Posts by Tag

• Review 625
• Reinforcement Learning 117
• Large Language Models 88
• Diffusion Models 60
• Benchmark 37
• LLMs 35
• Vision-Language Models 27
• Chain-of-Thought 24
• Large Language Models (LLMs) 23
• Multimodal AI 22
• Tool Use 22
• Generative Models 21
• LLM Evaluation 20
• Agentic AI 18
• Policy Optimization 18
• Reasoning 17
• LLM Agents 17
• Generative AI 17
• Transformer 17
• Reinforcement Learning (RL) 16
• LLM 15
• Image Generation 15
• Benchmarking 14
• Embodied AI 14
• Code Generation 14
• Text-to-Image Generation 14
• Foundation Models 13
• Robotics 13
• Data Curation 13
• Multimodal LLMs 13
• Computational Efficiency 12
• Generalization 12
• Instruction Following 12
• Training-Free 12
• Transformer Architecture 11
• Deep Learning 11
• Retrieval-Augmented Generation 11
• Flow Matching 11
• Contrastive Learning 11
• Dataset 11
• Mathematical Reasoning 10
• Fine-tuning 10
• Self-Supervised Learning 9
• 3D Gaussian Splatting 9
• Data Augmentation 9
• Multi-Agent Systems 9
• Curriculum Learning 9
• Instruction Tuning 9
• Image Editing 9
• Autoregressive Models 9
• Vision-Language Models (VLMs) 9
• Supervised Fine-Tuning 9
• Video Generation 9
• Diffusion Model 9
• Gaussian Splatting 8
• Multimodal Learning 8
• Reward Modeling 8
• Language Models 8
• LLM Alignment 8
• Prompt Engineering 8
• Synthetic Data 8
• Visual Question Answering 8
• Multimodal Large Language Models 8
• GRPO 8
• Evaluation Metrics 8
• Self-supervised Learning 8
• Hallucination 8
• Question Answering 7
• MLLMs 7
• Software Engineering 7
• Multimodal Reasoning 7
• Text-to-Image 7
• Data Synthesis 7
• Explainable AI 7
• AI Agents 7
• Multimodal Large Language Models (MLLMs) 7
• Supervised Fine-tuning 7
• Dataset Creation 7
• Diffusion Transformer 7
• Natural Language Processing 7
• Scaling Laws 7
• Django 6
• Information Retrieval 6
• Spatial Reasoning 6
• Visual Grounding 6
• Scalability 6
• Multi-Agent System 6
• Large Language Model 6
• Foundation Model 6
• Mixture-of-Experts 6
• LoRA 6
• Temporal Consistency 6
• Benchmark Dataset 6
• Domain Adaptation 6
• Reward Design 6
• Large Reasoning Models 6
• Zero-Shot Learning 6
• Evaluation 6
• LLM Reasoning 6
• Multi-agent Systems 6
• Model Merging 6
• Robustness 6
• Novel View Synthesis 6
• Vision-Language Model 6
• Interpretability 5
• Preference Optimization 5
• 3D Reconstruction 5
• Vision-Language-Action Models 5
• Robot Manipulation 5
• 3D Vision 5
• Robotic Manipulation 5
• Catastrophic Forgetting 5
• Mixture-of-Experts (MoE) 5
• Self-Correction 5
• Diffusion Transformers 5
• Reward Hacking 5
• Math Reasoning 5
• Long Context 5
• Supervised Fine-Tuning (SFT) 5
• Computer Vision 5
• Test-Time Scaling 5
• Progressive Training 5
• Efficiency 5
• AI Safety 5
• Multimodal LLM 5
• Zero-shot Learning 5
• Reasoning Tasks 5
• Imitation Learning 5
• Model Compression 5
• Video Diffusion Models 5
• Latent Space 5
• Video Understanding 5
• RLVR 5
• Human-Computer Interaction 4
• Attention Mechanisms 4
• Automated Theorem Proving 4
• Iterative Refinement 4
• LLM-as-a-Judge 4
• Preference Learning 4
• Image Synthesis 4
• Reasoning Models 4
• Hallucination Mitigation 4
• Reward Model 4
• Automated Evaluation 4
• Supervised Fine-tuning (SFT) 4
• Multi-modal Learning 4
• Variational Autoencoder 4
• Verifiable Rewards 4
• Efficient Inference 4
• Open-Source 4
• Direct Preference Optimization (DPO) 4
• GUI Automation 4
• Fairness 4
• Policy Gradient 4
• Low-Resource Languages 4
• GUI Agents 4
• Virtual Try-On 4
• Attention Mechanism 4
• Retrieval Augmented Generation 4
• Few-shot Learning 4
• Bias Mitigation 4
• Mechanistic Interpretability 4
• Diffusion Language Models 4
• Text Generation 4
• Diffusion LLMs 4
• Identity Preservation 4
• CLIP 4
• Vision Transformer 4
• Medical Imaging 4
• Visual Reasoning 4
• Camera Pose Estimation 4
• Depth Estimation 4
• Agentic Reinforcement Learning 4
• RLHF 4
• Model Context Protocol (MCP) 4
• GUI Agent 4
• Long-Horizon Tasks 4
• Online RL 4
• Me 3
• Jenkins 3
• Knowledge Distillation 3
• Transformer Models 3
• Residual Learning 3
• Recommender Systems 3
• Human-in-the-Loop 3
• Multi-Task Learning 3
• Multi-task Learning 3
• Survey 3
• MLLM 3
• Training-free 3
• VQA 3
• Exploration-Exploitation 3
• Cross-Attention 3
• Safety Alignment 3
• Lifelong Learning 3
• Fine-Tuning 3
• LLM Safety 3
• Dataset Generation 3
• LLM Inference 3
• Parameter Efficiency 3
• Reinforcement Learning from Human Feedback 3
• Framework 3
• Markov Decision Process 3
• Continual Learning 3
• GAIA Benchmark 3
• PPO 3
• Chain-of-Thought (CoT) 3
• KV Cache Optimization 3
• Speech Recognition 3
• Exploration 3
• Speech Synthesis 3
• Text-to-Speech 3
• Self-Play 3
• Computer Graphics 3
• GUI Grounding 3
• Multimodal Understanding 3
• Training Efficiency 3
• Adversarial Attack 3
• Mixture of Experts 3
• Sparse Attention 3
• Normalization 3
• Vision-Language-Action (VLA) Models 3
• ASR 3
• Multi-turn Dialogue 3
• Audio-Language Models 3
• Long-Horizon Planning 3
• Multi-view Synthesis 3
• Regularization 3
• Agent Evaluation 3
• Remote Sensing 3
• Parallel Decoding 3
• Model Distillation 3
• Multimodal Models 3
• Visual Perception 3
• Context-Awareness 3
• Pass@k 3
• Sim-to-Real Transfer 3
• Video Synthesis 3
• Controllable Generation 3
• Supervised Learning 3
• Tool-Integrated Reasoning 3
• Calibration 3
• Quantization 3
• Adaptive Sampling 3
• Process Reward Models 3
• Financial Reasoning 3
• 3D Scene Generation 3
• Text-to-Video 3
• Image-to-Video 3
• Long Video Understanding 3
• Human Motion Synthesis 3
• Multimodal Generation 3
• Scientific Reasoning 3
• Hallucinations 3
• 3D Generation 3
• Data Diversity 3
• Unified Framework 3
• Synthetic Data Generation 3
• Post-training 3
• Deep Research 3
• Docker 2
• Ambiguity Resolution 2
• Machine Unlearning 2
• Model Editing 2
• Arabic NLP 2
• NeRF 2
• Hybrid Model 2
• Scene Representation 2
• Sparse View 2
• Linear Attention 2
• Transformer Architectures 2
• Perception 2
• Direct Preference Optimization 2
• Formal Verification 2
• Lean 2
• Multi-view Learning 2
• Pre-training 2
• Inference Optimization 2
• 3D Gaussian Splatting (3DGS) 2
• Conversational AI 2
• Video Segmentation 2
• End-to-End Learning 2
• Test-time Scaling 2
• Resource Allocation 2
• LLM Training 2
• CTF Challenges 2
• Vision-Language-Action (VLA) 2
• Cybersecurity 2
• DPO 2
• Content Moderation 2
• Brain-inspired AI 2
• Dense Retrieval 2
• RAG 2
• Parameter-Efficient Learning 2
• Visual Language Models 2
• Data Visualization 2
• Hallucination Detection 2
• Zero-Shot Generalization 2
• LLM Agent 2
• Visual Quality 2
• Autoregressive Generation 2
• Pose Control 2
• Discrete Diffusion 2
• Visual Understanding 2
• Unified Architecture 2
• Natural Language Understanding 2
• Autonomous Driving 2
• Agent Frameworks 2
• Optimization 2
• Resource Management 2
• Actor-Critic 2
• 4D Generation 2
• Instance Segmentation 2
• U-Net 2
• Data Flywheel 2
• UI Automation 2
• Model Pruning 2
• Memory Optimization 2
• Audio Understanding 2
• Multimodality 2
• Peer Review 2
• Out-of-Distribution 2
• Computer Use Agent 2
• Text-to-3D Generation 2
• Multi-modal Large Language Models 2
• Text-to-Audio 2
• Multi-Turn Interaction 2
• Cognitive Reasoning 2
• Benchmark Evaluation 2
• Document Understanding 2
• Large Multimodal Models 2
• Evaluation Framework 2
• Action Planning 2
• LLM Efficiency 2
• World Model 2
• Robotics Simulation 2
• Human Evaluation 2
• Overthinking 2
• Iterative Reasoning 2
• Sociolinguistics 2
• Model Evaluation 2
• Label-Free Learning 2
• Neural Radiance Fields (NeRF) 2
• Interactive Editing 2
• Real-time Rendering 2
• Semantic Alignment 2
• 3D Scene Reconstruction 2
• Memory Management 2
• 3D Mesh Generation 2
• Text-to-3D 2
• Code Reasoning 2
• CoT Compression 2
• Reproducibility 2
• 데이터 필터링 2
• Misinformation 2
• Rectified Flow 2
• LLM Compression 2
• Loss Aggregation 2
• Visual Generation 2
• Robot Learning 2
• Multimodal Retrieval 2
• Multilingual NLP 2
• Agentic Search 2
• Information Seeking 2
• 대규모 언어 모델 2
• 멀티모달 AI 2
• Encoder-Decoder 2
• Game AI 2
• Deep Search 2
• 3D World Generation 2
• Large-scale Dataset 2
• Test-Time Optimization 2
• Video Question Answering 2
• Reasoning Benchmark 2
• Image Processing 2
• Distribution Shift 2
• DiT 2
• Low-Rank Adaptation 2
• Animation 2
• Explainable AI (XAI) 2
• Human Feedback 2
• Multimodal 2
• Pseudo-labeling 2
• Knowledge Retrieval 2
• Graph Neural Networks 2
• Point Clouds 2
• Transformer Networks 2
• AGI 2
• Video Editing 2
• Deep Reasoning 2
• OCR 2
• State Space Models 2
• Prompt Sensitivity 2
• Proactive AI 2
• Generation Process 2
• Adaptive Learning 2
• Uncertainty Quantification 2
• Holistic Evaluation 2
• Medical Image Segmentation 2
• Mask-Free 2
• Image Inpainting 2
• Systematic Review 2
• Attention Control 2
• LLM Optimization 2
• AI for Science 2
• Financial LLMs 2
• Live Benchmark 2
• Data Contamination 2
• Web Search 2
• FP8 Training 2
• 3D Editing 2
• Multi-View Consistency 2
• Educational Assessment 2
• Commonsense Reasoning 2
• AI Ethics 2
• Language Models (LLMs) 2
• Multimodal Agents 2
• Temporal Grounding 2
• Scientific Discovery 2
• Parameter-Efficient Fine-Tuning 2
• Human-Robot Interaction 2
• Medical Diagnosis 2
• Clinical Decision Support 2
• Out-of-Distribution Generalization 2
• Adaptive Reasoning 2
• Neural Networks 2
• Paraphrasing 2
• Accessibility 2
• Inference Efficiency 2
• Context Length 2
• 3D Consistency 2
• Surface Reconstruction 2
• Speech Tokenizer 2
• Semantic Reasoning 2
• Autoregressive Model 2
• Parallel Training 2
• Benchmarks 2
• Diffusion Transformers (DiT) 2
• Generalization Gap 2
• Neural Radiance Fields 2
• Semantic Features 2
• Deep Research Agents 2
• Factual Accuracy 2
• Report Generation 2
• Research Automation 2
• Vulnerability Detection 2
• Tree Search 2
• Advantage Estimation 2
• Mixture of Experts (MoE) 2
• Robot Control 2
• Streaming Inference 2
• Preference Alignment 2
• Next-Token Prediction 2
• LLM Fine-tuning 2
• Sparsification 2
• Image-to-3D 2
• Video Diffusion 2
• Human Perception 2
• Dynamic Scenes 2
• Image Customization 2
• Evaluation Benchmark 2
• Function Calling 2
• Dynamic Environments 2
• Speculative Decoding 2
• Hyperparameter Tuning 2
• AdamW 2
• Positional Encoding 2
• Self-Improvement 2
• Knowledge Transfer 2
• DINOv3 2
• Data Collection 2
• Agent Framework 2
• Agentic Systems 2
• Few-Step Generation 2
• Multi-Turn Reasoning 2
• Procedural Content Generation 2
• Dataset Annotation 2
• LLM-based Agents 2
• Natural Language Interaction 2
• Adversarial Training 2
• Web Agents 2
• Long-Horizon Reasoning 2
• Data Generation 2
• 4D World Modeling 2
• Machine Translation 2
• Multilingual 2
• Slow Thinking 2
• Style Transfer 2
• Unified Models 2
• Efficient AI 2
• Multi-hop QA 2
• Multi-turn Interaction 2
• Context Management 2
• State-of-the-Art 2
• Mode Collapse 2
• Memory Efficiency 2
• SafeLine 1
• Logging 1
• GitHub Actions 1
• Nginx 1
• Chrome Extension 1
• AWS 1
• Lambda 1
• EventBridge 1
• Agriculture 1
• Disease Identification 1
• Pest Management 1
• Crop Management 1
• Agronomy 1
• Kolmogorov-Arnold Networks 1
• Art Style Classification 1
• Spline-Based Activation 1
• Dual-Teacher 1
• Gram Matrix 1
• Spoken Dialogue Models 1
• Bilingual Benchmark 1
• Complex Conversations 1
• Context Understanding 1
• Influence Function 1
• Incremental Learning 1
• Privacy Protection 1
• Gradient Optimization 1
• Dense Passage Retrieval 1
• Attentive Relevance Scoring 1
• Semantic Matching 1
• Flow Equivariance 1
• Recurrent Neural Networks 1
• Sequence Models 1
• Group Equivariance 1
• Lie Subgroups 1
• Time-Parameterized Symmetries 1
• Joint Optimization 1
• Neural Rendering 1
• Softmax Attention 1
• Recurrent Neural Networks (RNNs) 1
• Taylor Series Expansion 1
• Expressiveness 1
• Persona Control 1
• Activation Steering 1
• Finetuning 1
• Behavioral Shift Detection 1
• Data Filtering 1
• GUI grounding 1
• AI agent 1
• Large Multi-modal Model 1
• User Intent Modeling 1
• Multi-Stage Training 1
• E-commerce 1
• Filter Bubble Mitigation 1
• Matthew Effect 1
• Visuomotor Agents 1
• Minecraft 1
• Cross-View Goal Specification 1
• Automated Task Synthesis 1
• Geometry Reasoning 1
• Lemma-Style Proving 1
• Hallucination Reduction 1
• Min-Max Optimization 1
• Token-Adaptive Strategy 1
• Spectral Regularization 1
• Feed-forward Models 1
• Latent Actions 1
• Proprioceptive Feedback 1
• 3D Vision-Language Models 1
• Scene Understanding 1
• Dynamic View Selection 1
• Diffusion Large Language Models 1
• Variable-Length Generation 1
• Dynamic Length Adaptation 1
• Denoising Strategy 1
• Image-goal Navigation 1
• Incremental Scene Representation 1
• Coarse-to-fine Localization 1
• Differentiable Rendering 1
• LLM Hallucination 1
• Low-resource Languages 1
• ROUGE Score 1
• Cross-lingual Evaluation 1
• Factual Consistency 1
• Multi-Turn Dialogue Evaluation 1
• Multi-Judge Aggregation 1
• Dialogue Quality Assessment 1
• Maximum Likelihood Estimation 1
• Referring Segmentation 1
• Image Segmentation 1
• Neural Fields 1
• Pixel Space 1
• Fault Localization 1
• Issue Resolution 1
• Competitive Debate 1
• Graph Traversal 1
• Software Issue Resolution 1
• Experience-Driven Learning 1
• Automated Program Repair 1
• Knowledge Management 1
• Continuous Learning 1
• Audio-driven Video Generation 1
• Spatial Auditory Cues 1
• Video Scene Layout 1
• Large Vision-Language Models (LVLMs) 1
• Visual Token Pruning 1
• Dynamic Compression 1
• GlimpsePrune 1
• Compute Optimization 1
• Multi-stage Tasks 1
• Search Efficiency 1
• Self-Supervised RL 1
• AI Scientist 1
• Virtual Cell Modeling 1
• Single-Cell Perturbation Prediction 1
• Automated Model Design 1
• Cybersecurity Agents 1
• Trajectory Synthesis 1
• Runtime-Free Training 1
• LLM Simulation 1
• Meta-RL 1
• Emergent Behavior 1
• Multi-Armed Bandits 1
• Gridworlds 1
• Pseudo-Thompson Sampling 1
• Cyber Threat Intelligence 1
• Chatbot 1
• Personalized Safety Alignment 1
• Text-to-Image Diffusion Models 1
• User Preferences 1
• Text Rendering 1
• Multimodal Diffusion Transformer 1
• Multi-memory Systems 1
• Knowledge Graph 1
• Closed-Loop Planning 1
• Context-Aware Embedding 1
• Long Document Comprehension 1
• Semantic Association 1
• Text Embedding 1
• Omni-modal LLMs 1
• Distributed Training 1
• Model-centric 1
• Parallelism 1
• FSDP 1
• Sequence Parallelism 1
• Expert Parallelism 1
• Alignment Preservation 1
• Fisher Information Matrix 1
• Riemannian Geometry 1
• Approximate Nearest Neighbor Search 1
• Code Optimization 1
• HNSW 1
• Chart Captioning 1
• Cycle Consistency 1
• Reference-Free Metric 1
• Answer Verification 1
• Formula Verification 1
• Model Averaging 1
• Multi-Image Composition 1
• Layout Control 1
• Tool-use 1
• MCP 1
• Large-scale 1
• Real-world tasks 1
• Meta-tool-learning 1
• Ultra-long Video Generation 1
• Multimodal Guidance 1
• Controllable Video Generation 1
• Degradation-aware Training 1
• Multi-human Video Generation 1
• Interactive Talking 1
• Audio-driven Animation 1
• Speech Interaction 1
• Non-Autoregressive Inference 1
• High-Speed Inference 1
• Alignment Drift 1
• Training Data Provenance 1
• Belief Conflict Index (BCI) 1
• Suffix Array 1
• Safety Interventions 1
• Issue Localization 1
• Tool-integrated Agents 1
• Code Search 1
• 3D Occupancy Grounding 1
• Voxel-based Prediction 1
• Coarse-to-Fine 1
• Hierarchical RL 1
• Training-Agent Disaggregation 1
• Observability 1
• 3D Anomaly Detection 1
• Kernel Attention 1
• Learnable Advisor 1
• Parameter Perturbation 1
• Point Cloud 1
• Industrial AI 1
• Toxicity Prediction 1
• Drug Development 1
• Cheminformatics 1
• Interpretable AI 1
• IUPAC Nomenclature 1
• Video Virtual Try-On 1
• Stage-Wise Framework 1
• Garment Preservation 1
• C-to-Rust Conversion 1
• Project-Level Translation 1
• Code Synthesis 1
• Memory Safety 1
• Software Migration 1
• Hybrid Translation 1
• Cost Efficiency 1
• Performance-Cost Trade-off 1
• Synthetic Worlds 1
• Transfer Learning 1
• Video-to-3D Synthesis 1
• Latent Space Modeling 1
• Temporal Coherence 1
• Human Preference Score 1
• Image Evaluation 1
• Uncertainty-Aware Ranking Loss 1
• Query-based Model 1
• Transformer Decoder 1
• Biomedical Imaging 1
• Cell Segmentation 1
• OOD Generalization 1
• Data Distribution Shift 1
• Pattern Matching 1
• DataAlchemy 1
• Design-to-Code 1
• Webpage Generation 1
• Layout Preservation 1
• Efficient Decoding 1
• Static Sparsity 1
• Entropy Regularization 1
• Self-Checking 1
• Previewing 1
• Audio-Language Model 1
• General Audio Captions 1
• Public Datasets 1
• Biomedical NER 1
• Named Entity Recognition 1
• Healthcare AI 1
• AI Conferences 1
• Sustainability 1
• Community Building 1
• Environmental Impact 1
• Mental Health 1
• Centralized Model 1
• Decentralized Model 1
• Capability Collapse 1
• Hybrid Policy Optimization 1
• Multiple Importance Sampling 1
• Root Cause Analysis 1
• 5G Wireless Networks 1
• TeleLogs Dataset 1
• Self-Evolving 1
• Experiential Learning 1
• Specialist-to-Generalist 1
• Active Context Management 1
• Proactive Interference 1
• Tool Augmentation 1
• Working Memory 1
• Context Curation 1
• Visual Analytics 1
• 3D Model Evaluation 1
• Music Restoration 1
• Audio Mastering 1
• Audio Quality Enhancement 1
• Social Intelligence 1
• Utterance-level Rewards 1
• Multi-dimensional Rewards 1
• Partial Observability 1
• SOTOPIA 1
• Cross-Attention Analysis 1
• Content-Style Disentanglement 1
• Artistic Style Transfer 1
• SDXL 1
• DAPO 1
• Autonomous Agents 1
• SWE-BENCH 1
• Web Agent 1
• Knowledge-Induced 1
• Large Multimodal Models (LMMs) 1
• Bloom's Taxonomy 1
• Web-CogDataset 1
• Web-CogBench 1
• Well-being Concepts 1
• Principle-Guided Evaluation 1
• Explanation Generation 1
• Multi-hop Reasoning 1
• Evaluation Dataset 1
• Input Scrutiny 1
• Error Detection 1
• Faulty Inputs 1
• Modality Preference 1
• Cross-Modal Inconsistency 1
• AI Agent 1
• Multi-agent System 1
• Programmatic Control 1
• OSWorld Benchmark 1
• Hybrid AI 1
• Vision Language Models (VLMs) 1
• Physical Reasoning 1
• Simulation Environments 1
• Interactive AI 1
• Efficient Reasoning 1
• Model Optimization 1
• Model Collaboration 1
• Overthinking Problem 1
• Customer Support 1
• Dialogue Generation 1
• Role-Playing 1
• COPC Framework 1
• Strategy Prediction 1
• Empathetic AI 1
• Policy Learning 1
• 3D Generation Evaluation 1
• Hierarchical Evaluation 1
• Material Properties 1
• Multi-Agent Annotation 1
• Hybrid Scoring System 1
• Video-based Evaluation 1
• Part-level Analysis 1
• Multi-hop Question Answering 1
• Reasoning Errors 1
• Error Taxonomy 1
• Multimodal Entity Linking 1
• Collaborative Reflection 1
• Visual Information 1
• Text-centric 1
• LLM Bias 1
• Hiring Evaluation 1
• Linguistic Shibboleth 1
• Hedging Language 1
• Sample Efficiency 1
• Multi-dimensional Filtering 1
• Video Object Segmentation 1
• Complex Scenes 1
• Object Tracking 1
• Dataset Challenges 1
• Voice Cloning 1
• Emotion Control 1
• Disentanglement 1
• Emotional Speech Dataset 1
• Reward Rectification 1
• Dynamic Fine-Tuning (DFT) 1
• PII Redaction 1
• Privacy Preservation 1
• Cross-Domain Generalization 1
• Open-Source LLMs 1
• Self-Evolving LLM 1
• Zero-Data Training 1
• Simultaneous Speech Translation 1
• Adaptive Policy 1
• Entropy-based Loss 1
• Mutual Information 1
• Latency-Quality Trade-off 1
• Speech-to-Text Translation 1
• REINA 1
• Robust PCA 1
• Deep Unfolding 1
• Sparse Segmentation 1
• Image Decomposition 1
• Image Compression 1
• One-Step Decoding 1
• Fidelity Guidance 1
• Rate Annealing 1
• VAE 1
• Perceptual Quality 1
• Strand Generation 1
• Sketch Guidance 1
• Multi-scale Learning 1
• Adaptive Conditioning 1
• 3D Hair Modeling 1
• Visual Document Understanding 1
• Mixed Reward Modeling 1
• Unsupervised Adaptation 1
• Test-Time Adaptation (TTA) 1
• Domain Transfer 1
• Gaussian Splatting (GS) 1
• 3D Scene Representation 1
• Physics Simulation 1
• Ray Tracing 1
• Exploration Strategy 1
• Adaptive Exploration Reward 1
• Multi-view Relighting 1
• Material-guided 1
• Inverse Rendering 1
• Consistent Relighting 1
• Cultural Groundedness 1
• Linguistic Capability 1
• Multilingual AI 1
• Procedural Memory 1
• Task Automation 1
• Experience Replay 1
• Agent Learning 1
• Mesh Understanding 1
• Primitive-Mesh Decomposition 1
• Surprisal 1
• Pruning 1
• Grounding 1
• Reward Function 1
• Resampling 1
• Visual Noise Reduction 1
• Virtual Try-Off 1
• Bidirectional Learning 1
• Fashion Synthesis 1
• Self-Evolving AI Agents 1
• Agent Optimization 1
• CLIP Latent 1
• ControlNet 1
• Deep-Research Agents 1
• Retrieval 1
• Curated Corpus 1
• Transparency 1
• Step Entropy 1
• SFT 1
• 사전 학습 1
• 변조 저항성 1
• 바이오위협 1
• AI 안전 1
• 서킷 브레이킹 1
• 머신 언러닝 1
• Poisoning Attack 1
• Fact-checking 1
• System Security 1
• Shape Transformation 1
• Trajectory Divergence Map 1
• Region Control 1
• Sequence Classification 1
• Multi-label Classification 1
• GLiNER 1
• MoE Architecture 1
• Dynamic Activation 1
• Adjugate Experts 1
• Upcycling Strategy 1
• Load Balancing 1
• Reasoning LLMs 1
• Gradient Clipping 1
• Global Locality 1
• Matrix Decomposition 1
• Action Reasoning 1
• Spatial Planning 1
• Depth Perception 1
• Trajectory Generation 1
• Visual Effects 1
• Spatial Control 1
• Multi-VFX 1
• Agent Reasoning 1
• Physical Interaction 1
• Constraint Reasoning 1
• Clipping 1
• Overlong Filtering 1
• Passage Ranking 1
• Listwise Reranking 1
• Computer Vision (CV) 1
• Shortcut Learning 1
• Dataset Diversity 1
• Dataset Fragmentation 1
• Speech-to-LaTeX 1
• Mathematical Expression Recognition 1
• LaTeX Generation 1
• Self-Rewarding LLMs 1
• Gradient Collapse 1
• Iterative Optimization 1
• User-Centric AI 1
• Interactive Agents 1
• Gym Environment 1
• Preference Elicitation 1
• Long Document Understanding 1
• Visual QA 1
• Table Understanding 1
• Jailbreak Attack 1
• Adversarial Audio 1
• Projected Gradient Descent 1
• Native Payload Discovery 1
• Multimodal AI Safety 1
• Structured Output 1
• Video Promotion 1
• Text-to-Video Retrieval 1
• Modality Refinement 1
• Black-box Attack 1
• Video Manipulation 1
• Transferability 1
• Language Model 1
• JEE 1
• 코드 생성 1
• 코드 벤치마크 1
• 다국어 프로그래밍 1
• 자동화된 데이터 생성 1
• 샌드박스 평가 1
• Asynchronous RL 1
• Attention Steering 1
• Stereotype Analysis 1
• Quantum Game Theory 1
• NISQ Hardware 1
• Error Mitigation 1
• Battle of the Sexes 1
• Qiskit 1
• Quantum Computing 1
• Strategic Coordination 1
• Payoff Maximization 1
• 4D Character Animation 1
• Character Dataset 1
• Next Shot Generation 1
• In-Context Tuning 1
• Cinematic Continuity 1
• Hierarchical Prompting 1
• Shot Editing 1
• Decoder-Centric 1
• Intermediate Supervision 1
• Out-of-Domain Generalization 1
• Internal Language Model 1
• Diplomacy Game 1
• Strategic Reasoning 1
• Behavioral Analysis 1
• Automated Environment Generation 1
• Feedback-Driven Training 1
• Reward Mechanism 1
• Contextual Understanding 1
• Replay 1
• Activation States 1
• Anti-forgetting 1
• Threshold-based Margin Loss 1
• Hierarchical Reinforcement Learning 1
• Multi-source RAG 1
• Knowledge Integration 1
• Enterprise Search 1
• Panoramic Video Generation 1
• Camera Control 1
• Paralinguistic Vocalizations 1
• Data Annotation 1
• Mandarin Speech 1
• Expressive Speech 1
• Computer-Use Agents 1
• Chain-of-Thought Reasoning 1
• Open-source Framework 1
• Desktop Automation 1
• Region Consistency 1
• Spatial Voting 1
• Temporal Oscillation 1
• Self-Consistency Voting 1
• Temporal Semantic Entropy 1
• Low-Resource MT 1
• Back-Translation 1
• In-Context Learning (ICL) 1
• Topic-Guided Generation 1
• Parallel Data Synthesis 1
• Robotic Dexterous Grasping 1
• Affordance-Aware 1
• Human-like Priors 1
• Two-Stage Training 1
• Manipulation 1
• Reasoning Efficiency 1
• Token Budget Control 1
• Group Relative Policy Optimization 1
• Masked Generative Transformers 1
• Compositional Generation 1
• Attention Guidance 1
• Unmasking Strategy 1
• Attribute Binding 1
• Mesh Generation 1
• Level of Detail (LOD) 1
• Progressive Meshes 1
• Vertex Split 1
• 3D Graphics 1
• Spatio-Temporal Fusion 1
• Land Surface Temperature 1
• Generative Adversarial Network 1
• Weakly-Supervised Learning 1
• Meta-learning 1
• Adaptive Control 1
• Agent Stability 1
• Dynamic Supervision 1
• Maneuvering 1
• Explainable NLP 1
• Natural Language Explanations 1
• Pre-trained Language Models 1
• Natural Language Inference 1
• Model Performance Enhancement 1
• Hybrid Annotation 1
• Faster Inference 1
• Discrete Diffusion Forcing (D2F) 1
• GPT-4o 1
• Surreal Image Generation 1
• Artifact Restoration 1
• Sparse-view 3D Reconstruction 1
• Reference-Guided 1
• Backdoor Attack 1
• Input-aware Trigger 1
• Security 1
• Open-vocabulary 1
• Group Relative Alignment Optimization 1
• Self-Optimization 1
• Real-World Benchmark 1
• K-12 Education 1
• Molecule Discovery 1
• Molecular Generation 1
• Hypernetworks 1
• Reward-Guided Generation 1
• Latent Space Optimization 1
• Multimodal Agent 1
• Long-Term Memory 1
• Episodic Memory 1
• Semantic Memory 1
• Entity-Centric Memory 1
• Plug-and-Play 1
• Self-Attention 1
• Lightweight AI 1
• Conditional Image Branch 1
• Storyboard Generation 1
• Character Consistency 1
• Scene Diversity 1
• Visual Storytelling 1
• Task Vectors 1
• Coding LLM 1
• Automated Interpreting Assessment 1
• SHAP 1
• Interpreting Quality 1
• Human-Centered AI 1
• Empathy 1
• MLLM Benchmark 1
• Continuous Latent Tokens 1
• Long-Context Understanding 1
• LLMs Evaluation 1
• Global Comprehension 1
• Fluid Intelligence 1
• Prequel Entailment 1
• Visual Encoders 1
• Metadata 1
• Image Acquisition 1
• Causal Transformer 1
• Sequential Modeling 1
• Streaming Data 1
• Pointmap Prediction 1
• Online Perception 1
• KVCache 1
• Cartoon Generation 1
• Post-Keyframing 1
• Sparse Control 1
• UI Agent 1
• RFT 1
• UI Grounding 1
• UI Navigation 1
• Data Cleaning 1
• Self-Evolving Trajectory 1
• Visual Mathematical Reasoning 1
• Knowledge System 1
• Dataset Construction 1
• Mathematical Benchmark 1
• Natural Language Processing (NLP) 1
• Post-hoc Explainability 1
• Differential Privacy (DP) 1
• Privacy-Utility Trade-off 1
• Model Faithfulness 1
• Text Privatization 1
• Reward Models 1
• Guided Decoding 1
• Object Precision 1
• Object Recall 1
• Inference-time Control 1
• Dense Feature Maps 1
• Gram Anchoring 1
• Geospatial AI 1
• Audio-Driven Animation 1
• Multi-Objective Optimization 1
• Timestep-Layer Adaptive 1
• Masked Autoencoder 1
• Earth Observation 1
• Multitemporal 1
• Multispectral 1
• Fusion Strategies 1
• Target Normalization 1
• 논문 검색 1
• 계층적 인덱싱 1
• 유연한 검색 1
• 정보 추출 1
• 뷰 인식 1
• 강화 학습 1
• Semi-supervised Learning 1
• GAN-based Methods 1
• Image-to-image Translation 1
• Ensemble Learning 1
• Self-Search 1
• 3D Morphable Model 1
• Face Stylization 1
• Text-to-Image Translation 1
• Attribute Preservation 1
• 3D Dataset 1
• High-Resolution Textures 1
• Physically Based Rendering (PBR) 1
• 3D Animation 1
• GPT-5 Annotations 1
• Sketchfab 1
• Sandbox 1
• Self-Explanation 1
• Node Classification 1
• Dynamic 3D 1
• Single Image Input 1
• Large Reasoning Models (LRMs) 1
• Incomplete Problems 1
• CRITIC-math 1
• Cognitive-Inspired RAG 1
• Stateful Reasoning 1
• Long Narrative Comprehension 1
• Dynamic Memory 1
• Metacognitive Regulation 1
• Multi-step Retrieval 1
• Hierarchical Knowledge Source 1
• Multi-Modal Fusion 1
• Prior Information 1
• Spatial Intelligence 1
• GPT-5 1
• Cognitive AI 1
• Structured Reasoning 1
• Virtual Worlds 1
• RPG 1
• Agent Systems 1
• Combat Simulation 1
• Alignment Pre-training 1
• Text-to-Vision Mapping 1
• Continuous Representations 1
• Video Relighting 1
• Background Replacement 1
• Interactive Video Generation 1
• Real-Time AI 1
• Auto-Regressive Generation 1
• Data Pipeline 1
• Self-Forcing 1
• KV Caching 1
• Granularity Control 1
• Structured Representation 1
• Hierarchical Generation 1
• Coarse-to-fine 1
• Visual Tokenization 1
• Native Resolution Vision 1
• Chart Analysis 1
• Action-to-Video Generation 1
• Visual Action Prompts 1
• Skeleton Representation 1
• Human-Object Interaction 1
• Cross-Domain Transfer 1
• Rubric-based Reward 1
• RLVR Extension 1
• Human-centric AI 1
• Reward Hacking Mitigation 1
• Speech Representation Learning 1
• Cochlear Tokens 1
• Biologically Inspired AI 1
• Audio Processing 1
• Classifier-free Guidance 1
• Self-Guidance 1
• Stochastic Block-Dropping 1
• Efficient Architectures 1
• Transformer Optimization 1
• LLM Robustness 1
• In-Context Learning 1
• Batch Calibration 1
• Template Ensembles 1
• Self-Refinement 1
• Speech Separation 1
• Deep Neural Networks 1
• Cocktail Party Problem 1
• Unsupervised Learning 1
• Datasets 1
• Moral Reasoning 1
• Bayesian Evaluation 1
• Soft Labels 1
• Multi-Agent Reinforcement Learning 1
• Continuous Control 1
• Pathfinding 1
• MARL Benchmark 1
• GPU Acceleration 1
• Heterogeneous Agents 1
• Chain-of-Agents 1
• Agent Foundation Models 1
• Multi-agent Distillation 1
• LLM Copyright Protection 1
• Model Fingerprinting 1
• Text Watermarking 1
• Invasive Fingerprinting 1
• Intrinsic Fingerprinting 1
• Intellectual Property 1
• Digital Rights Management 1
• Backdoor Watermarking 1
• Sparse Autoencoders 1
• LLM Steering 1
• Feature Selection 1
• Correlation Analysis 1
• Video Recommendation 1
• Content-Based Filtering 1
• Pointing 1
• Zero-shot Generalization 1
• Podcast Recommendation 1
• Offline Evaluation 1
• User Profiling 1
• Affective Computing 1
• Misery Score Prediction 1
• Gamified Evaluation 1
• Feedback-driven Adaptation 1
• Unposed Reconstruction 1
• Incremental Optimization 1
• Octree 1
• Long Videos 1
• Multimodal Browsing 1
• Audio Intelligence 1
• Long-Form Audio 1
• Multicultural Music 1
• SAM 1
• Zero-Order Optimization 1
• Bayesian Optimization 1
• Confidence Estimation 1
• Fine-Grained 1
• Monte Carlo Sampling 1
• Backward Confidence Integration 1
• Motion Transfer 1
• Cross-topology 1
• Sparse Correspondence 1
• Motion Matching 1
• Controllable Image Generation 1
• Multi-modal Generation 1
• Visual References 1
• Image-to-Image 1
• MLLM-as-a-Judge 1
• ID Consistency 1
• Wearable Objects 1
• Markup Language 1
• Structured Prompting 1
• IDE Support 1
• Multimodal Data 1
• Styling System 1
• Development Toolkit 1
• Radiance Fields 1
• XR 1
• View Synthesis 1
• Immersive Technology 1
• Search and Recommendation 1
• Semantic IDs 1
• Bi-Encoder 1
• Human Preference Alignment 1
• Temporal Credit Assignment 1
• Text-Guided Editing 1
• Color Editing 1
• Multi-Modal AI 1
• Image Manipulation 1
• Zero-shot HAR 1
• Time-Series Analysis 1
• Knowledge Base 1
• Multi-sensor Fusion 1
• Self-Verification 1
• Dual Learning 1
• Multilingual Translation 1
• Autonomous Scientific Discovery 1
• Scientific Workflow Automation 1
• Natural Sciences 1
• Cognitive Diagnosis Model 1
• Knowledge Assessment 1
• Matrix Factorization 1
• CPA-QKA 1
• Future Prediction 1
• Dynamic Evaluation 1
• Financial Forecasting 1
• Fully Homomorphic Encryption (FHE) 1
• TFHE 1
• Levenshtein Distance 1
• Programmable Bootstrapping (PBS) 1
• Privacy-Preserving Computation 1
• String Similarity 1
• Scale Equivariance 1
• Deep Equilibrium Models 1
• Canonicalization 1
• Image Classification 1
• Semantic Segmentation 1
• Latent Representation 1
• Monotone Scaling 1
• Model Context Protocol 1
• Real-World Applications 1
• Unknown Tools 1
• Structured Mesh 1
• Blender Python 1
• Shape Editing 1
• Part-based Representation 1
• Hybrid Architecture 1
• Mamba-Transformer 1
• Reasoning LLM 1
• High Throughput 1
• On-Policy RL 1
• Off-Policy Experts 1
• Dynamic Weighting 1
• Post-training Quantization (PTQ) 1
• Activation Outliers 1
• Quantization Methods 1
• Efficient Deployment 1
• Multi-modal Recommendation 1
• Graph Neural Network 1
• Homography Relations 1
• Meta-network 1
• Orthogonal Constraint 1
• Data Sparsity 1
• Embodied Cognition 1
• Sparse Input 1
• Scene Completion 1
• Vision Language Models 1
• Vietnamese Language 1
• Cross-Lingual Reasoning 1
• ViExam 1
• Multilingual Benchmark 1
• Reasoning Taxonomy 1
• Benchmark Scaling 1
• Cultural Nuances 1
• Parametric Human Model 1
• 3D Human Modeling 1
• Shape-Skeleton Decoupling 1
• Pose Correctives 1
• Single Image Mesh Fitting 1
• Expressive Modeling 1
• Goliath Dataset 1
• LLM Benchmarks 1
• General Capabilities 1
• Domain-Specific Benchmarks 1
• Target-Specific Benchmarks 1
• Confidence Filtering 1
• Self-Consistency 1
• Early Stopping 1
• Majority Voting 1
• Domain Specialization 1
• Best-of-N Selection 1
• AI Companionship 1
• Human-AI Interaction 1
• Emotional AI 1
• Boundary Setting 1
• Psychological Frameworks 1
• Multimodal Foundation Model 1
• Scientific AI 1
• Dynamic Tokenizer 1
• Low-Resource Learning 1
• Real-world Tasks 1
• Error Analysis 1
• Foundational Models 1
• Cross-Platform 1
• Single-Image Input 1
• Feedforward Networks 1
• Geometric Modeling 1
• Texture Synthesis 1
• Feature Aggregation 1
• 3D Human Reconstruction 1
• Two-Image Input 1
• Real-time Inference 1
• Point Cloud Prediction 1
• Feed-forward Network 1
• Super-Resolution 1
• Video-LLM 1
• Object Segmentation 1
• Open Access 1
• Prompt Injection 1
• Competitive Programming 1
• Test Case Generation 1
• Programming Competitions 1
• Algorithmic Problems 1
• Agentic Applications 1
• ReAct Paradigm 1
• Developer Experience 1
• Variational Problem Synthesis 1
• Policy Entropy 1
• Reasoning Benchmarks 1
• Annotated Data 1
• Model Stability 1
• Concept Unlearning 1
• Sparse Autoencoders (SAEs) 1
• Model Interpretability 1
• Safety-Critical AI 1
• Feature Suppression 1
• WMDP Benchmark 1
• False Premise Detection 1
• Clarification 1
• Egocentric Video Generation 1
• Viewpoint Alignment 1
• Causal Interplay 1
• First-Person Vision 1
• Agentic RAG 1
• Traceable AI 1
• Human Reasoning Styles 1
• Social Deduction Games 1
• Theory of Mind 1
• Avalon Game 1
• Cognitive Grounding 1
• LLM Jailbreaking 1
• Red Teaming 1
• Malicious Content Detection 1
• Developer Messages 1
• D-Attack 1
• DH-CoT 1
• Adversarial Attacks 1
• Dataset Cleaning 1
• Inverse Kinematics 1
• Human Pose Estimation 1
• SMPL Model 1
• Optimization-Free 1
• Data-Driven 1
• Weakly Supervised Learning 1
• Affordance Grounding 1
• Part Discovery 1
• Object Localization 1
• DINO 1
• Reasoning Depth 1
• Cellular Automata 1
• Recurrence 1
• Adaptive Computation Time 1
• Exploration Bottleneck 1
• Instructional Scaffolding 1
• Rubric-based Rewards 1
• General Reasoning 1
• RL with Verifiable Rewards 1
• Compositional Visual Reasoning 1
• Tool Learning 1
• Text Simplification 1
• Readability Control 1
• German NLP 1
• LLM Distillation 1
• Multi-level Text Generation 1
• Versatility 1
• Softmax 1
• Gradient Sensitivity 1
• Token Separability 1
• GPT-2 1
• Multimodal Language Models 1
• Multilingual Benchmarking 1
• Persian Language 1
• Cultural Nuance 1
• Multiview Diffusion 1
• Out-of-Domain 1
• Image Retrieval 1
• Hybrid Training 1
• Sparse-View 1
• 2DGS 1
• Generalizable 1
• Mesh Extraction 1
• LLMs as Judges 1
• NLG Evaluation 1
• Measurement Theory 1
• Validity 1
• Reliability 1
• Evaluation Bias 1
• Responsible AI 1
• Multi-Agent LLMs 1
• Academic Poster Generation 1
• Aesthetic Design 1
• Layout Optimization 1
• Typography 1
• Color Palette 1
• VLM-as-Judge 1
• Content Fidelity 1
• Semi-structured Tables 1
• Hierarchical Orthogonal Tree 1
• Table Layout Understanding 1
• Pipeline Generation 1
• Verification Mechanism 1
• Visually-Guided Image Editing 1
• Idiom Interpretation 1
• Textual Image Design 1
• Entity Reasoning 1
• Multimodal LLM Evaluation 1
• Speech Language Modeling 1
• Low Bitrate Codec 1
• End-to-End Training 1
• Binary Spherical Quantization 1
• Unsolved Questions 1
• AI Benchmark 1
• Oracle-Free Validation 1
• Generator-Validator Gap 1
• Community Evaluation 1
• Stack Exchange 1
• Chain of Thought 1
• Stage-Aware Rewards 1
• Universal Model 1
• Mamba 1
• Streaming Video 1
• Condensed Matter Physics 1
• Evaluation Metric 1
• Expression Edit Distance 1
• Problem Solving 1
• High-Resolution Generation 1
• UNet Architecture 1
• DiT Architecture 1
• Scale Fusion 1
• LoRA Fine-tuning 1
• Legal AI 1
• Claim Generation 1
• Chinese Legal Dataset 1
• Factuality 1
• Clarity 1
• Zero-shot Evaluation 1
• Reasoning Probing 1
• Component Decoupling 1
• Bidirectional Transformer 1
• Fidelity Enhancement 1
• Prediction Filtering 1
• Token Efficiency 1
• Artistic Meshes 1
• Video Question Answering (VQA) 1
• System-2 Thinking 1
• Multi-agent LLMs 1
• Movie Understanding 1
• Cinematic Content 1
• Agentic Enhancement 1
• 3D Inpainting 1
• Multi-view Consistency 1
• 3D Object Completion 1
• Video Avatar Generation 1
• Cognitive Simulation 1
• Multimodal Fusion 1
• Contextual Animation 1
• Sparsity 1
• Memorization 1
• Top-k Routing 1
• 3D Physics Prediction 1
• CLIP Features 1
• Material Point Method 1
• PIXIEVERSE Dataset 1
• Contextual Bandits 1
• Query Rewriting 1
• No-Regret Learning 1
• Academic Survey 1
• Citation Verification 1
• Decontextualization 1
• Keyword Graph 1
• Scientific Ideation 1
• Inspiration Engine 1
• Controllable Reasoning 1
• Reasoning Compression 1
• Budget-Aware Training 1
• Execution Environments 1
• Automated Training 1
• Verifiable Feedback 1
• Segment-level Decoding 1
• Memory Networks 1
• Long-Context Learning 1
• Sparse Models 1
• Network Community Structure 1
• Cognitive Skills 1
• AI Interpretability 1
• Module Communities 1
• Neural Plasticity 1
• Long-form Audio 1
• Multi-speaker 1
• Next-token Diffusion 1
• Audio Compression 1
• 3D Inversion 1
• Contextual Feature Replacement 1
• Edit3D-Bench 1
• Audio-Driven Video Generation 1
• Cinematic Video 1
• Long Video Consistency 1
• Human Animation 1
• Multimodal Control 1
• Long-Form Audio Generation 1
• Narrative Reasoning 1
• Logit Lens 1
• Linear Probing 1
• Activation Patching 1
• Repetitions 1
• Planner-Executor Architecture 1
• Decoupled Training 1
• Large Vision-Language Models 1
• Specialization 1
• Generative Research Synthesis 1
• LLM-as-a-judge 1
• Related Work Generation 1
• Verifiability 1
• DLM Acceleration 1
• Early Answer Convergence 1
• Early Commit Decoding 1
• Confidence Gap 1
• Inference Speedup 1
• Action Decoding 1
• Masked Modeling 1
• Adaptive Decoding 1
• rPPG 1
• Multi-View Video Dataset 1
• Health Biomarkers 1
• Physiological Monitoring 1
• Telemedicine 1
• Biosignals 1
• Digital Human Synthesis 1
• Real-time Video Generation 1
• Autoregressive LLM 1
• Deep Compression Autoencoder 1
• Exposure Bias Mitigation 1
• Multimodal LLMs (MLLMs) 1
• Smartphone Agents 1
• Privacy Awareness 1
• Sensitive Data Detection 1
• Risk Assessment 1
• Text-Guided Motion Generation 1
• Rectified Flow Matching 1
• Real-time AI 1
• Language Modeling 1
• Multi-Token Prediction 1
• Token Order Prediction 1
• Auxiliary Objective 1
• Learning-to-Rank 1
• Self-Rewarding 1
• Reasoning Decomposition 1
• Language Reasoning 1
• Language Shortcuts 1
• Generative Judges 1
• Stepwise Feedback 1
• Meta-Reasoning 1
• Autoscaling 1
• Disaggregated Architecture 1
• Heterogeneous Hardware 1
• Topology-aware Scheduling 1
• GPU Utilization 1
• Distributed Systems 1
• Experience Generation 1
• AWORLD Framework 1
• Vision-Language-Action Model 1
• Instruction-Driven Routing 1
• Cognition-Aligned AI 1
• Triplane Representation 1
• Collaborative Coding 1
• Multi-modal Conditioning 1
• Garment Transfer 1
• Pose Animation 1
• Fashion Tech 1
• CondNet 1
• Deepfake Detection 1
• Partial Deepfakes 1
• AI-Generated Video 1
• Video Forensics 1
• Manipulation Detection 1
• Cross-Domain Orchestration 1
• Fuzzy Instructions 1
• Multi-Step Tasks 1
• Real-World Scenarios 1
• Long Video Generation 1
• Context Routing 1
• 3D Point Tracking 1
• Multi-View 1
• kNN Correlation 1
• Occlusion Handling 1
• Feature Fusion 1
• Human-Computer Interaction (HCI) 1
• Goal Tracking 1
• Visualization 1
• Multi-Turn Dialogue 1
• User Interface Design 1
• Sensemaking 1
• Mask-Guided Editing 1
• Human Preference Learning 1
• Persuasion Dynamics 1
• Gullibility 1
• Receptiveness 1
• Pairwise Preference 1
• Stable Optimization 1
• UniGenBench 1
• In-Tool Learning 1
• In-Weight Learning 1
• Factual Recall 1
• Video Object Removal 1
• Side Effects 1
• 3D Rendering 1
• Video Inpainting 1
• Difference Mask 1
• Instruction Augmentation 1
• Task-Centric 1
• Task Alignment 1
• Breadth-First Search 1
• Constraint Generation 1
• Alignment Amplification 1
• Rank-One Update 1
• Weight Steering 1
• Jailbreak Robustness 1
• Fine-tuning-free 1
• Safety Injection 1
• Style-Driven Generation 1
• Subject-Driven Generation 1
• Disentangled Representation 1
• Reward Learning 1
• Cross-Task Learning 1
• Code Interpreter 1
• GRPO-RoC 1
• LLM Training Efficiency 1
• Self-Reflection 1
• AI-Generated Code Security 1
• Repository-Level Benchmark 1
• Code Security 1
• Static Analysis 1
• Bias Detection 1
• Scientific LLMs 1
• Scientific Data 1
• Multimodal Integration 1
• Knowledge Representation 1
• Autonomous Discovery 1
• Data Ecosystems 1
• Symmetry Detection 1
• Equivariant Networks 1
• Geometric Deep Learning 1
• Spatial Consistency 1
• Semantic Knowledge 1
• Code Embeddings 1
• Code Generation Models 1
• Autoregressive Backbones 1
• Last-Token Pooling 1
• MTEB Benchmark 1
• Multimodal Pretraining 1
• Real-world Robotics 1
• Dexterous Manipulation 1
• Mobile Manipulation 1
• Human-to-Robot Learning 1
• Sim2Real 1
• Depth Image 1
• Visual Localization 1
• Bimanual Control 1
• Physics Formula Discovery 1
• Symbolic Regression 1
• Causal Chain of Thought 1
• UI Agents 1
• Human-Agent Interaction 1
• Mixed-Initiative AI 1
• User Choice 1
• Blind and Low-Vision Users 1
• Auto-Thinking 1
• Bi-mode Annealing 1
• Bi-mode Policy Optimization (BPO) 1
• General-Purpose AI 1
• Audio-Driven Talking Head Synthesis 1
• Large-Scale Dataset 1
• Algorithmic Fairness 1
• Procedural Knowledge 1
• Declarative Knowledge 1
• Strategic Decision-Making 1
• Language Model Pre-training 1
• Dynamic Data Mixing 1
• Data Influence 1
• Group Influence 1
• Regression Model 1
• Foundational Model 1
• Planning 1
• Data Engineering 1
• Chinese App Scenarios 1
• Spatial Cognition 1
• Embodied Agents 1
• Cognitive Map 1
• Spatial Memory 1
• Navigation 1
• Input Reformulation 1
• τ-bench 1
• Context Engineering 1
• Multi-Agent Framework 1
• Surface Defect Detection 1
• Anomaly Detection 1
• Mixed Supervision 1
• Industrial Inspection 1
• Unified Model 1
• Critic-Free RL 1
• Agentic Reasoning 1
• Group Sampling 1
• Static Value Estimation 1
• Table-to-Report Generation 1
• Industrial Applications 1
• Table Reasoning 1
• Real-world Data 1
• Arabic LLM 1
• UI-level Evaluation 1
• ALLaM 34B 1
• HUMAIN Chat 1
• Dialectal Arabic 1
• LLM as a Judge 1
• Safety Evaluation 1
• Constitutional AI 1
• Inference-Time Control 1
• Indian Sociocultural Context 1
• Genetic Algorithms 1
• Textual Data Augmentation 1
• Active Learning 1
• NLP 1
• Medical AI 1
• Verifier System 1
• Patient Simulator 1
• Clinical Rubrics 1
• Baichuan-M2 1
• HealthBench 1
• LLM Optimizers 1
• AdEMAMix 1
• MARS 1
• Weight Decay 1
• Object Detection 1
• Global Scene Context 1
• Context-Aware Fusion 1
• Fine-grained Detection 1
• Automotive Damage Assessment 1
• Generative Denoising 1
• Dynamic Clipping 1
• Advantage Standardization 1
• Noise Inversion 1
• Gumbel-max Trick 1
• Location-aware Argmax Inversion 1
• Semantic Aggregation 1
• Video MLLM 1
• VideoQA 1
• Deep Learning Optimizers 1
• Pretraining Speedup 1
• Matrix-based Optimizers 1
• Data-to-Model Ratio 1
• Cacheable Architecture 1
• Multi-Reference 1
• Semi-Attention 1
• Adventure Games 1
• Full Story Arc 1
• Observation-Behavior Gap 1
• Video Compositing 1
• Position Embedding 1
• Masked Token Injection 1
• Video Harmonization 1
• Cross-Entropy Loss 1
• Large Vision and Language Models (LVLMs) 1
• Peer Learning 1
• Diversity Optimization 1
• Quality Enhancement 1
• Semantic Clustering 1
• Slow-Fast Encoding 1
• Human Alignment 1
• Native-Resolution Vision Encoder 1
• Critic Models 1
• Policy Models 1
• Self-Criticism 1
• Medical Image Retrieval 1
• Zero-shot 1
• MAE 1
• SimDINO 1
• Vision Foundation Models 1
• Vision Transformers (ViT) 1
• CT Imaging 1
• Low-Bit Quantization 1
• Spectral Decomposition 1
• Anisotropy 1
• Adaptive Learning Rate 1
• FP4 Training 1
• Mobile Agents 1
• Agent Acceleration 1
• Vision Encoder 1
• Generative Pretraining 1
• Captioning Loss 1
• Image-Text Models 1
• 문서 변환 1
• 시각-언어 모델 1
• 자가 개선 1
• 합성 데이터 1
• 증류 없는 학습 1
• Reasoning Vectors 1
• Task Arithmetic 1
• Parameter Transfer 1
• Text-to-SQL 1
• Error Correction 1
• Query Planning 1
• Database Interaction 1
• Multi-turn Reasoning 1
• Gradient Explosion 1
• Training Stability 1
• Trajectory Filtering 1
• Zero RL 1
• Metalinguistic Reasoning 1
• Constructed Language 1
• Camlang 1
• Second Language Acquisition 1
• Sequential Decision Making 1
• Autonomous AI 1
• Point Cloud Learning 1
• Cross Reconstruction 1
• Decoupled Views 1
• Multi-Turn RL 1
• Hybrid Environments 1
• Parameter Interpolation 1
• Customizable Strategies 1
• User-Defined Agents 1
• Sandboxed Execution 1
• Reinforcement Learning from Verifiable Rewards (RLVR) 1
• Asynchronous Execution 1
• Multi-modal AI 1
• Monocular SLAM 1
• Dense Reconstruction 1
• Pose Graph Optimization 1
• Intrinsics-free 1
• Real-time 1
• Two-view Association 1
• Knowledge Acquisition 1
• Pretraining Data 1
• Entity Linking 1
• Coreference Resolution 1
• Model Analysis 1
• Checkpoints 1
• Multi-Subject Generation 1
• Personalized Image Synthesis 1
• Semantic Correspondence 1
• Attention Disentanglement 1
• Face Generation 1
• Multimodal Synthesis 1
• Semantic Control 1
• Hierarchical Constraint Satisfaction Problems 1
• Human-Robot Interaction (HRI) 1
• Task Planning 1
• Chain-of-Thought (CoT) Reasoning 1
• Research Agents 1
• Seminar-Grounded Tasks 1
• Data Leakage Prevention 1
• Ill-Structured Problems 1
• LLM Embedding 1
• Delta Activations 1
• Finetuned Models 1
• Model Representation 1
• Model Clustering 1
• Additive Property 1
• Task Embedding 1
• CAD Generation 1
• Vector Graphics 1
• Sequence-to-Sequence Learning 1
• Engineering Drawings 1
• Soft Target Loss 1
• Dual Decoder 1
• Pragmatic Understanding 1
• Drivelology 1
• Contextual Inference 1
• Portrait Animation 1
• Attribute Transfer 1
• Dual Reference Networks 1
• Self-Reconstruction 1
• Facial Editing 1
• Malicious Input Detection 1
• Probing Classifiers 1
• Superficial Patterns 1
• Instructional Patterns 1
• Trigger Words 1
• Flow-based Models 1
• Few-step Sampling 1
• Marginal-Data Transport 1
• Velocity Matching 1
• Velocity Distillation 1
• Dense Geometry Estimation 1
• Normal Estimation 1
• Logarithmic Quantization 1
• Cognitive Inertia 1
• Named Entity Retrieval 1
• Type-Aware Embeddings 1
• Internal Representations 1
• Post-Training 1
• Hybrid Algorithms 1
• Bias-Variance Tradeoff 1
• Training Objective 1
• Continuous-Time Dynamics 1
• State Transition 1
• Scalable Training 1
• Video Segment Selection 1
• Bi-level Reward 1
• Behavioral Evaluation 1
• Model Alignment 1
• Sycophancy 1
• World Model Brittleness 1
• Metacognition 1
• Personality Profiling 1
• Autocurriculum 1
• Task-Space Exploration 1
• Inference-Time Iteration 1
• Unreal Engine 5 1
• Interactive Environments 1
• Sim-to-Real 1
• Spatial Understanding 1
• Multimodal Input 1
• Lighting Estimation 1
• HDR Environment Map 1
• Video Transformer 1
• 3D CT 1
• Diagnostic Error Reduction 1
• Multi-scale Alignment 1
• Semantic Enrichment 1
• Radiology Reporting 1
• Model Robustness 1
• Benchmark Reliability 1
• Linguistic Variability 1
• Language Model Inference 1
• Acceleration 1
• Set Block Decoding 1
• Next Token Prediction 1
• Masked Token Prediction 1
• KV-caching 1
• Symbolic Graphics Programming 1
• SVG Generation 1
• Text-to-Image Synthesis 1
• Cross-Modal Alignment 1
• Program Synthesis 1
• Teleoperation 1
• Low-Cost Hardware 1
• 3D Printing 1
• Leader-Follower System 1
• Robotics Interface 1
• Open Source 1
• Pretraining 1
• Binary Classification 1
• Symbolic Music Reasoning 1
• Music Score Analysis 1
• In-the-Wild Data 1
• Music Theory 1
• Online 3D Reconstruction 1
• Streaming Reconstruction 1
• Sliding Window 1
• Camera Token Pool 1
• Real-time Performance 1
• Dark Humor Detection 1
• Iterative Reasoning Refinement 1
• Meme Analysis 1
• Cross-Modal Attention 1
• 2D/3D Classification 1
• Segmentation 1
• T2I Benchmarking 1
• Compositional Reasoning 1
• Deductive Inference 1
• Inductive Inference 1
• Abductive Inference 1
• MLLM Evaluation 1
• Noise Suppression 1
• Visual Complexity 1
• Interleaving Reasoning 1
• Fine-grained Detail 1
• Multilingual LLM 1
• Low-Resource Language 1
• German 1
• Bavarian Dialect 1
• Cross-Lingual Transfer 1
• Continuous Pretraining 1
• Llama-3.1 1
• Model Expansion 1
• Mobile GUI Agents 1
• Hybrid Automation 1
• Shortcut Generation 1
• Task Efficiency 1
• Mobile Robotics 1
• Research Reproducibility 1
• Scientific Communication 1
• Genomics 1
• Single-Cell Analysis 1
• Spatial Transcriptomics 1
• Tool Usage 1
• Perception-heavy Benchmarks 1
• Vision Tools 1
• Deep Research Systems 1
• Hierarchical Agents 1
• RL Frameworks 1
• Open-Ended Generation 1
• Reverse-Engineered Reasoning (REER) 1
• Perplexity Minimization 1
• DeepWriting-20K 1
• Trajectory-aware RL 1
• Value Model 1
• Masked Diffusion Models 1
• Resistant AI 1
• Resilient AI 1
• Coevolution 1
• Fast-Slow Models 1
• AGI Alignment 1
• TPTP Ecosystem 1
• Saturation Proving 1
• Proof Graph Reconstruction 1
• LLM Step-Provers 1
• Off-Policy RL 1
• Automated Theorem Proving (ATP) 1
• Formal Mathematics 1
• AlphaZero 1
• Knowledge-Intensive Tasks 1
• Unified Audio-Video Generation 1
• Stitching of Experts (SoE) 1
• Multimodal Diffusion 1
• Online Annotation 1
• Cross-modal Noise Correlation 1
• Verse-Bench 1
• Web Navigation 1
• Causal Attention 1
• Lookahead Keys 1
• Autoregressive Modeling 1
• Perplexity Reduction 1
• Radiology 1
• Computed Tomography (CT) 1
• Magnetic Resonance Imaging (MRI) 1
• Cross-Modality Generalization 1
• Human Preference 1
• Direct-Align 1
• SRPO 1
• Fine-Grained Control 1
• Flow Matching Models 1
• Vision-Language-Action 1
• Visual Foresight 1
• Predictive Inverse Dynamics 1
• Mixture-of-Transformer 1
• Multi-stage Training 1
• Data-Free Training 1
• Visual Search 1
• Tool-Integrated Agents 1
• Exploratory Reasoning 1
• Over-turn Masking 1
• Parallel Thinking 1
• Progressive Curriculum 1
• Exploration Scaffold 1
• Noise Scheduling 1
• Post-Training Quantization 1
• Image Quality Metrics 1
• Latent Consistency Models 1
• Unified Multimodal Models 1
• Reconstruction Alignment 1
• Visual Embeddings 1
• LLM Factuality 1
• Parametric Knowledge 1
• Hint Scaffolding 1
• Item Response Theory 1
• Exploration Efficiency 1
• Problem Difficulty 1
• Multi-Identity Generation 1
• Identity Consistency 1
• Identity Confusion 1
• Matching Reward 1
• Global Assignment 1
• Visual Representation Alignment 1
• Fine-grained Visual Understanding 1
• Object Counting 1
• Gradient Variance 1
• Unbiased Estimator 1
• 3D World Modeling 1
• Predictive Models 1
• LiDAR 1
• Occupancy Grids 1
• Long-Horizon Decision Making 1
• Progressive Scaling 1
• Code Repository 1
• Agentization 1
• Agent-to-Agent Protocol 1
• Human Agency 1
• AI Assistants 1
• Sociotechnical AI 1
• AI Alignment 1
• Scalable Evaluation 1
• Weak-to-Strong Learning 1
• 3D Part Segmentation 1
• Point Cloud Segmentation 1
• Prompt-based Segmentation 1
• Interactive Segmentation 1
• Automatic Segmentation 1
• Native 3D 1
• VLM 1
• Reward Scaling 1
• Generative Paradigm 1
• Context Scaling 1
• Toxic Text Generation 1
• Text Detoxification 1
• Lexical Diversity 1
• Human Annotation 1
• 2D Gaussian Splatting 1
• DINO Features 1
• Patch-level Rasterization 1
• Continuous Representation 1
• Auto-Encoder 1
• Image-to-Text 1
• Reconstruction Fidelity 1
• Speech-to-Speech LLMs 1
• Acoustic-Semantic Gap 1
• Echo Training 1
• Unit Language 1
• Knowledge-based QA 1
• Reasoning Dataset 1
• Generation Chain-of-Thought 1
• Image Aesthetics 1
• Prompt Alignment 1
• Text-based Person Retrieval 1
• Dual-Masking 1
• Gradient-Attention 1
• WebPerson Dataset 1
• Policy Gradients 1
• Entropy Modulation 1
• Credit Assignment 1
• Uncertainty 1
• Self-Calibrating Gradient Scaling 1
• Human-Centric Video Generation 1
• Multimodal Conditioning 1
• Audio-to-Video 1
• Subject Preservation 1
• Audio-Visual Synchronization 1
• Avatar Animation 1
• Multimodal Instructions 1
• Long-Duration Video Generation 1
• MLLM Director 1
• Cascaded Framework 1
• Lip Synchronization 1
• Instruction Grounding 1
• Video Diffusion Transformers 1
• Long-Context LLMs 1
• Code Evaluation 1
• Multi-file Reasoning 1
• Architectural Understanding 1
• Software Development Lifecycle 1
• Metrics 1
• Multimodal Recommendation 1
• Modality Alignment 1
• Dilated Convolution 1
• Maximum Mean Discrepancy 1
• Dimensionality Reduction 1
• 3D Grounding 1
• Task-Adaptive Reasoning 1
• Embodiment-Aware Planning 1
• LLM Security 1
• Data Poisoning 1
• Backdoor Attacks 1
• CoT Unfaithfulness 1
• Emergent Robustness 1
• Data Scarcity 1
• Video Dataset 1
• Spatial Annotation 1
• Depth Map 1
• Structured Caption 1
• Motion Instruction 1
• World Modeling 1
• Diversity Collapse 1
• f-divergence 1
• Forward-KL 1
• JS-divergence 1
• Model Adaptation 1
• Bridge Attention 1
• Low-resource Training 1
• Visual Programmability 1
• Code-as-Thought (CaT) 1
• Chart Understanding 1
• Dual-Reward System 1
• Headline Generation 1
• Minority Languages 1
• Low-Resource NLP 1
• Natural Language Generation 1
• Chinese Minority Languages 1
• Generalist Robot Policies 1
• Intermediate Fusion 1
• Noise Resistance 1
• Query Decomposition 1
• Adaptive Retrieval 1
• Heuristic Framework 1
• Revelator 1
• Resolution-Agnostic 1
• VAE Decoder 1
• High-Resolution Image Generation 1
• Inpainting 1
• Educational Dialogue 1
• Engagement Modeling 1
• Second Language Learning 1
• Readability Metrics 1
• Long-tailed Learning 1
• Semi-Supervised Learning 1
• Open-World Scenarios 1
• OOD Detection 1
• Confidence Calibration 1
• Language Agents 1
• Real-World Performance 1
• High-Frequency Trading 1
• Technical Analysis 1
• Algorithmic Trading 1
• Price-Driven Signals 1
• Execution Capability 1
• Self-Conditioning 1
• Thinking Models 1
• Voice Style Adaptation 1
• Spoken Language Models 1
• LALM-as-a-Judge 1
• Speech Generation 1
• Virtual Economy 1
• Economic Mechanisms 1
• Governance 1
• Blockchain 1
• Agent Alignment 1
• 3D Shape Decomposition 1
• Part-level Generation 1
• Bounding Box Prompts 1
• Sentiment Analysis 1
• Narrative Analysis 1
• Decentralized Social Media 1
• Bluesky 1
• Topic Modeling 1
• Real-time Processing 1
• Video Hallucination 1
• Large Video Models (LVMs) 1
• Hierarchical Reasoning 1
• Spatial-Temporal Grounding 1
• Diagnostic Framework 1
• Ethical Reasoning 1
• Mental Health AI 1
• Human-in-the-loop 1
• Embedding Models 1
• Gradient Alignment 1
• Fisher Information 1
• 3D Scene Dataset 1
• Simulation Environment 1
• Scene Generation 1
• Point-Goal Navigation 1
• Realistic Layouts 1
• Object Interaction 1
• Real-to-Sim 1
• Multi-Modal Transformers 1
• Drag-based Editing 1
• Explicit Correspondence 1
• Multi-objective Reinforcement Learning 1
• Dynamic Reward Weighting 1
• Pareto Front Optimization 1
• Hypervolume Indicator 1
• Gradient-based Optimization 1
• Locality 1
• Data Statistics 1
• Optimal Denoiser 1
• Wiener Filter 1
• Sensitivity Fields 1
• Inductive Bias 1
• Reflection 1
• Visual Attention 1
• Information Loss 1
• Embeddings 1
• Connectors 1
• k-NN Overlap Ratio 1
• Embedding Reconstruction 1
• Epistemic Humility 1
• False-Option Rejection 1
• Scene Graph 1
• Multi-Modal Dataset 1
• Multi-Domain Data 1
• Geometric Foundation Models 1
• Spatio-Temporal Data 1
• Dataset Benchmark 1
• Multimodal Dataset 1
• Behavioral Traits 1
• Causal Representation Learning 1
• Big Five 1
• Causal Discovery 1
• Semi-online RL 1
• Offline RL 1
• Patch Module 1
• Region Prompting 1
• Unified Representation 1
• Efficiency Optimization 1
• Token Cost 1
• Sampling Cost 1
• Dynamic CoT Switching 1
• Quantum Algorithms 1
• Lattice Problems 1
• Coset Sampling 1
• Quantum Fourier Transform (QFT) 1
• Modular Arithmetic 1
• Quantum Cryptography 1
• Exact Sampling 1
• 3D Asset Generation 1
• AI Pipeline 1
• Game Development 1
• Neural Modules 1
• Retopology 1
• UV Unwrapping 1
• Science AI 1
• Caption-assisted Reasoning 1
• SeePhys Challenge 1
• Physics Problems 1
• Cross-modal Alignment 1
• Multiple Instance Learning 1
• Hard Instance Mining 1
• Computational Pathology 1
• Whole Slide Images 1
• Masked Learning 1
• Siamese Network 1
• Medical Image Analysis 1
• Post-training Quantization 1
• Hessian-based Optimization 1
• Error Compensation 1
• Low-bit LLMs 1
• Summarization 1
• ReAct 1
• Agentic LLMs 1
• Continual Pre-training 1
• Multi-step Reasoning 1
• Variance Reduction 1
• Environment Scaling 1
• Tool-Augmented LLMs 1
• Knowledge Graphs 1
• Open-Ended Deep Research 1
• Dynamic Outline 1
• Evidence Acquisition 1
• Hierarchical Writing 1
• Memory Bank 1
• Multidisciplinary 1
• Scoring System 1
• FP8 Quantization 1
• Data Bootstrapping 1
• Language-Centric AI 1
• Context Fidelity 1
• Retrieval-Augmented Generation (RAG) 1
• In-context Retrieval 1
• Advertisement Video Analysis 1
• Real-world Scenarios 1
• Challenge Benchmark 1
• Omnidirectional Vision 1
• Panoramic Perception 1
• Dataset Development 1
• Robot Navigation 1
• System Architecture 1
• SAIL-ViT 1
• Code Language Models 1
• Sensitive Memorization 1
• Privacy 1
• Gradient Ascent 1
• Model Utility 1
• Representation Steering 1
• Behavioral Entanglement 1
• Harmful Generation 1
• Hallucination Control 1
• Modular Framework 1
• Hierarchical Optimization 1
• Character Animation 1
• Video Replacement 1
• Relighting LoRA 1
• Holistic Replication 1
• Unified Visual Tokenizer 1
• 4D Representation 1
• Adversarial-free Training 1
• Reconstruction 1
• Semantic Understanding 1
• Ultrasound Imaging 1
• Label-free Reinforcement Learning 1
• Self-improvement 1
• Entropy Collapse 1
• Novelty Reward 1
• Test-Time RL 1
• Evolutionary Computing Principles 1
• Change Detection 1
• Frequency-Spatial Analysis 1
• Wavelet Transform 1
• Gated Fusion 1
• Agent Benchmarking 1
• Open-domain Search 1
• Time-Sensitive Data 1
• Reward Distribution Matching 1
• GFlowNets 1
• Diverse Reasoning 1
• Flow-Balanced Optimization 1
• Multiple-Choice QA 1
• Tokenization 1
• Accuracy 1
• Model Ranking 1
• Instruction-based Image Editing 1
• Multi-modal LLM 1
• Specification Alignment 1
• Test-Time Deliberation 1
• Safety-Behavior Trade-off 1
• ALIGN3 1
• SPECBENCH 1
• Agentic Recommender Systems 1
• Simulated Environments 1
• LLM-driven Simulation 1
• User Retention 1
• Vision-Language-Action (VLA) Model 1
• Human Demonstrations 1
• Video Generative Pretraining 1
• Ego-Centric Video 1
• Trajectory Prediction 1
• ActionVAE 1
• Computer Use Agents 1
• Cross-Platform Data 1
• Data Scaling 1
• Task Completion 1
• Masked Image Modeling 1
• LlamaGen 1
• Spatio-Temporal Video Grounding 1
• Decomposed Spatio-Temporal Highlighting 1
• Logit-Guided Re-attention 1
• Temporal-Augmented Assembling 1
• 3D/4D Generation 1
• Training-Free Guidance 1
• Camera Trajectory Control 1
• Geometric Consistency 1
• Inference-Time Optimization 1
• Dense Rewards 1
• Low-level Actions 1
• Human-GUI Interaction 1
• Cognitive Modeling 1
• Multimodal Reward Model 1
• MLLM Alignment 1
• Reward Head Architecture 1
• Ensemble Methods 1
• BaseReward 1
• Instruction-Guided TTS 1
• Expressive Speech Synthesis 1
• Subjective Evaluation 1
• Controllability 1
• Generative Modeling 1
• Representation Learning 1
• Classification 1
• Personalized Video Generation 1
• Adapter Networks 1
• Facial Recognition 1
• Hybrid Tokenizer 1
• Diffusion Decoder 1
• Model Scaling 1
• Camera Parameter Optimization 1
• RGB-Only Supervision 1
• Structure from Motion 1
• Outlier Robustness 1
• Two-stage Optimization 1
• Point Tracking 1
• Repository Planning 1
• Graph-based Representation 1
• Scalable Codebase 1
• Layout Guidance 1
• Synthetic Dataset 1
• Indoor Environments 1
• Semantic Consistency 1
• Role-playing Agents (RPAs) 1
• Dynamic Role Profiles 1
• Adaptive Temporal Sampling 1
• Text-Only Training 1
• Deep Supervision 1
• Whisper 1
• Encoder-Decoder Models 1
• Agent Environments 1
• Asynchronous Systems 1
• Multi-agent Collaboration 1
• Model Knowledge 1
• Closed-Book Question Answering (CBQA) 1
• Parameter Restoration 1
• Kullback-Leibler Divergence 1
• Knowledge Forgetting 1
• Auditory Knowledge 1
• Auditory Imagination 1
• Text-only Reasoning 1
• Parallel Manipulator 1
• Robotic Wrist 1
• Confined Space Manipulation 1
• Kinematics 1
• Anthropomorphic Robot 1
• Robot Design 1
• Code Review 1
• Python Projects 1
• End-to-End Evaluation 1
• Video Object Editing 1
• Adaptive Context Enrichment 1
• Guidance Responsiveness 1
• Cross-attention 1
• Speech-to-Text (S2T) 1
• Saliency Maps 1
• Feature Attribution 1
• Context Mixing 1
• Correlation 1
• Cultural Adaptation 1
• Indian Culture 1
• CSI 1
• Cultural Bias 1
• Forward Process 1
• CFG-free 1
• Negative-Aware FineTuning 1
• KV Cache Management 1
• Long Conversational QA 1
• Episodic Clustering 1
• Block Prefill Eviction 1
• Sensitivity-aware Allocation 1
• Reasoning Behaviors 1
• Contamination-Free 1
• Open-Source AI 1
• License Compliance 1
• License Drift 1
• AI Supply Chain 1
• Hugging Face 1
• GitHub 1
• LicenseRec 1
• Legal Risk 1
• Token Heterogeneity 1
• Advantage Redistribution 1
• Asymmetric Clipping 1
• Entropy-based RL 1
• Geometric Reasoning 1
• Two-stage Training 1
• GeoPQA Benchmark 1
• Perceptual Bottleneck 1
• AI Agency 1
• Less Is More 1
• Agentic Intelligence 1
• Efficiency Principle 1
• Multi-modal Foundation Model 1
• Simulated Environment 1
• Error Recovery 1
• Web Automation 1
• Late Interaction 1
• Meta Tokens 1
• Matryoshka Representation Learning 1
• Video Insertion 1
• Quantization-Aware PEFT 1
• Walsh-Hadamard Transform 1
• Sparse Adaptation 1
• Low-bit Quantization 1
• Multimodal Model 1
• Thinker-Talker Architecture 1
• Low-latency 1
• Cross-modal Reasoning 1
• Real-time Interaction 1
• Symbolic AI 1
• Adaptive Curricula 1
• First-Order Logic 1
• PDDL Planning 1
• Monte Carlo Annotation 1
• Noise Denoising 1
• Robust Learning 1
• Self-Supervision 1
• Contamination Resistance 1
• Enterprise Software 1
• Language Model Pretraining 1
• Inter-document Correlation 1
• Bootstrapping 1
• Concept Learning 1
• Video LLMs 1
• Off-policy Learning 1
• Reward Shaping 1
• Turkish NLP 1
• Token Classification 1
• ModernBERT 1
• Collaborative Filtering 1
• Embedding Scaling 1
• Noise Robustness 1
• Performance Degradation 1
• Cultural Heritage 1
• Ancient Greek Pottery 1
• Image Diffusion 1
• Sparse Anchor Views 1
• Small VLMs 1
• Large VLMs 1
• Model Parity Alignment 1
• Arabic OCR 1
• Markdown Conversion 1
• Conditional Generative Models 1
• Reparameterization 1
• Latent Space Alignment 1
• Visuomotor Policies 1
• Spatial Generalization 1
• Proprioception 1
• State-free Policies 1
• End-Effector Control 1
• Data Efficiency 1
• Sparse Voxels 1
• Geometric Accuracy 1
• Monocular Depth 1
• Voxel Uncertainty 1
• High-Quality Rendering 1
• Hybrid Representation 1
• Acceleration Framework 1
• Diffusion Distillation 1
• Bias 1
• German Dialects 1
• Stereotypes 1
• Implicit Association Test 1
• Decision Making 1
• Self-Distillation 1
• Dynamic 4D Generation 1
• Monocular Input 1
• Advantage Function 1
• Trajectory Certainty 1
• MLLM Efficiency 1
• Multimodal Transformer 1
• 3D-Resampler 1
• Document AI 1
• Hybrid Reinforcement Learning 1
• Robotics Data Curation 1
• Visual Temporal Progress 1
• Generative Value Learning (GVL) 1
• Task Progress Prediction 1
• Value-Order Correlation (VOC) 1
• Next-segment Reasoning 1
• Geospatial Reasoning 1
• Temporal Reasoning 1
• Travel Itinerary Reconstruction 1
• Agent System 1
• VLOG 1
• Voxel-Aligned Prediction 1
• Feed-Forward Reconstruction 1
• Reasoning Effectiveness 1
• Failed-Step Fraction 1
• Reasoning Graph 1
• Multi-spectral Imagery 1
• Gemini 2.5 1
• Land Cover Classification 1
• Pseudo-Image 1

Review

[논문리뷰] Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications

September 24, 2025

Genady Beryozkin이 [arXiv]에 게시한 ‘Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications’ 논문에 ...

[논문리뷰] What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT

September 24, 2025

Anthony Hartshorn이 [arXiv]에 게시한 ‘What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

September 24, 2025

Haoxiao Wang이 [arXiv]에 게시한 ‘VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction

September 24, 2025

So Fukuda이 [arXiv]에 게시한 ‘VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforcement Learning on Pre-Training Data

September 24, 2025

Evander Yang이 [arXiv]에 게시한 ‘Reinforcement Learning on Pre-Training Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OpenGVL - Benchmarking Visual Temporal Progress for Data Curation

September 24, 2025

Viktor Petrenko이 [arXiv]에 게시한 ‘OpenGVL - Benchmarking Visual Temporal Progress for Data Curation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe

September 24, 2025

Wenshuo Ma이 [arXiv]에 게시한 ‘MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MAPO: Mixed Advantage Policy Optimization

September 24, 2025

Xuankun Rong이 [arXiv]에 게시한 ‘MAPO: Mixed Advantage Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

September 24, 2025

Yifeng Jiang이 [arXiv]에 게시한 ‘Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Large Language Models Discriminate Against Speakers of German Dialects

September 24, 2025

Katharina von der Wense이 [arXiv]에 게시한 ‘Large Language Models Discriminate Against Speakers of German Dialects’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation

September 24, 2025

Jianbin Zheng이 [arXiv]에 게시한 ‘Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis

September 24, 2025

Dan Xu이 [arXiv]에 게시한 ‘HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction

September 24, 2025

Jin Zheng이 [arXiv]에 게시한 ‘GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Do You Need Proprioceptive States in Visuomotor Policies?

September 24, 2025

Yushen Liang이 [arXiv]에 게시한 ‘Do You Need Proprioceptive States in Visuomotor Policies?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching

September 24, 2025

Rui Qian이 [arXiv]에 게시한 ‘CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR

September 24, 2025

Zeina Aldallal이 [arXiv]에 게시한 ‘Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs

September 23, 2025

Anand Mishra이 [arXiv]에 게시한 ‘When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs’ 논문에...

[논문리뷰] VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models

September 23, 2025

Sunghyun Cho이 [arXiv]에 게시한 ‘VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery

September 23, 2025

Shiya Huang이 [arXiv]에 게시한 ‘VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Understanding Embedding Scaling in Collaborative Filtering

September 23, 2025

Yonghui Yang이 [arXiv]에 게시한 ‘Understanding Embedding Scaling in Collaborative Filtering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

September 23, 2025

Fatma Betül Terzioğlu이 [arXiv]에 게시한 ‘Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

September 23, 2025

Shaohui Jiao이 [arXiv]에 게시한 ‘TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Synthetic bootstrapped pretraining

September 23, 2025

Emmanuel Candès이 [arXiv]에 게시한 ‘Synthetic bootstrapped pretraining’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

September 23, 2025

Yannis Yiming He이 [arXiv]에 게시한 ‘SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning

September 23, 2025

Zhaopeng Tu이 [arXiv]에 게시한 ‘SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning

September 23, 2025

Damien Sileo이 [arXiv]에 게시한 ‘Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Qwen3-Omni Technical Report

September 23, 2025

Lhma-aslp이 [arXiv]에 게시한 ‘Qwen3-Omni Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models

September 23, 2025

Jae-Joon Kim이 [arXiv]에 게시한 ‘QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

September 23, 2025

Pengze Zhang이 [arXiv]에 게시한 ‘OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction

September 23, 2025

Xintao Chen이 [arXiv]에 게시한 ‘MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mano Report

September 23, 2025

Minghui Wu이 [arXiv]에 게시한 ‘Mano Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LIMI: Less is More for Agency

September 23, 2025

happyZYM이 [arXiv]에 게시한 ‘LIMI: Less is More for Agency’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning

September 23, 2025

Hou Pong Chan이 [arXiv]에 게시한 ‘GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token’s Nature

September 23, 2025

Bin Cui이 [arXiv]에 게시한 ‘From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token’s Nature’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem

September 23, 2025

Ahmed E. Hassan이 [arXiv]에 게시한 ‘From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions

September 23, 2025

tengdai722이 [arXiv]에 게시한 ‘FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questio...

[논문리뷰] EpiCache: Episodic KV Cache Management for Long Conversational Question Answering

September 23, 2025

Minsik Cho이 [arXiv]에 게시한 ‘EpiCache: Episodic KV Cache Management for Long Conversational Question Answering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

September 23, 2025

Qinsheng Zhang이 [arXiv]에 게시한 ‘DiffusionNFT: Online Diffusion Reinforcement with Forward Process’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultural Text Adaptation in Indian Context

September 23, 2025

Maunendra Sankar Desarkar이 [arXiv]에 게시한 ‘DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultur...

[논문리뷰] Cross-Attention is Half Explanation in Speech-to-Text Models

September 23, 2025

Luisa Bentivogli이 [arXiv]에 게시한 ‘Cross-Attention is Half Explanation in Speech-to-Text Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment

September 23, 2025

Yue Ma이 [arXiv]에 게시한 ‘ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects

September 23, 2025

Hang Yu이 [arXiv]에 게시한 ‘CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces

September 23, 2025

Jiafeng Xu이 [arXiv]에 게시한 ‘ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?

September 23, 2025

Jaeho Lee이 [arXiv]에 게시한 ‘AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels

September 23, 2025

Qi Zhang이 [arXiv]에 게시한 ‘Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ARE: Scaling Up Agent Environments and Evaluations

September 23, 2025

Matteo Bettini이 [arXiv]에 게시한 ‘ARE: Scaling Up Agent Environments and Evaluations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers

September 22, 2025

Karun Kumar이 [arXiv]에 게시한 ‘WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents

September 22, 2025

Chao Zhang이 [arXiv]에 게시한 ‘Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SPATIALGEN: Layout-guided 3D Indoor Scene Generation

September 22, 2025

Yongsen Mao이 [arXiv]에 게시한 ‘SPATIALGEN: Layout-guided 3D Indoor Scene Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation

September 22, 2025

Steven Liu이 [arXiv]에 게시한 ‘RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes

September 22, 2025

Narendra Ahuja이 [arXiv]에 게시한 ‘RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

September 22, 2025

jialingt이 [arXiv]에 게시한 ‘MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Lynx: Towards High-Fidelity Personalized Video Generation

September 22, 2025

Linjie Luo이 [arXiv]에 게시한 ‘Lynx: Towards High-Fidelity Personalized Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

September 22, 2025

Wenyu Wang이 [arXiv]에 게시한 ‘Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems

September 22, 2025

Hung-yi Lee이 [arXiv]에 게시한 ‘Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems’ 논문에 대...

[논문리뷰] BaseReward: A Strong Baseline for Multimodal Reward Model

September 22, 2025

jianfeipan이 [arXiv]에 게시한 ‘BaseReward: A Strong Baseline for Multimodal Reward Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent

September 22, 2025

Jiahui Yang이 [arXiv]에 게시한 ‘BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue

September 22, 2025

Hui Zhang이 [arXiv]에 게시한 ‘Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning

September 22, 2025

Jiangmiao이 [arXiv]에 게시한 ‘A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance

September 19, 2025

Ruibo Li이 [arXiv]에 게시한 ‘WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding

September 19, 2025

Rynson W. H. Lau이 [arXiv]에 게시한 ‘Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation

September 19, 2025

Xihui Liu이 [arXiv]에 게시한 ‘Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

September 19, 2025

Zehao Li이 [arXiv]에 게시한 ‘ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

September 19, 2025

SpaceProduct이 [arXiv]에 게시한 ‘RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RecoWorld: Building Simulated Environments for Agentic Recommender Systems

September 19, 2025

Mingyuan Wu이 [arXiv]에 게시한 ‘RecoWorld: Building Simulated Environments for Agentic Recommender Systems’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration

September 19, 2025

Zhilin Wang이 [arXiv]에 게시한 ‘Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks

September 19, 2025

Xijun Gu이 [arXiv]에 게시한 ‘MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs

September 19, 2025

Katharina von der Wense이 [arXiv]에 게시한 ‘Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FlowRL: Matching Reward Distributions for LLM Reasoning

September 19, 2025

Hengli Li이 [arXiv]에 게시한 ‘FlowRL: Matching Reward Distributions for LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning

September 19, 2025

Jiashuo Liu이 [arXiv]에 게시한 ‘FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection

September 19, 2025

Zhewei Zhang이 [arXiv]에 게시한 ‘FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation

September 19, 2025

Kishan Panaganti이 [arXiv]에 게시한 ‘Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence

September 19, 2025

Qinghua Huang이 [arXiv]에 게시한 ‘EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AToken: A Unified Tokenizer for Vision

September 19, 2025

Mingze Xu이 [arXiv]에 게시한 ‘AToken: A Unified Tokenizer for Vision’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Wan-Animate: Unified Character Animation and Replacement with Holistic Replication

September 18, 2025

Mingyang Huang이 [arXiv]에 게시한 ‘Wan-Animate: Unified Character Animation and Replacement with Holistic Replication’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning

September 18, 2025

Yicheng Pan이 [arXiv]에 게시한 ‘THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

September 18, 2025

Zhun Wang이 [arXiv]에 게시한 ‘SteeringControl: Holistic Evaluation of Alignment Steering in LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning

September 18, 2025

Zhou Yang이 [arXiv]에 게시한 ‘Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SAIL-VL2 Technical Report

September 18, 2025

Zijian Kang이 [arXiv]에 게시한 ‘SAIL-VL2 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era

September 18, 2025

Zihao Dongfang이 [arXiv]에 게시한 ‘PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook

September 18, 2025

Bowen Zhou이 [arXiv]에 게시한 ‘MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Improving Context Fidelity via Native Retrieval-Augmented Reasoning

September 18, 2025

Xiangru Tang이 [arXiv]에 게시한 ‘Improving Context Fidelity via Native Retrieval-Augmented Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale

September 18, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GenExam: A Multidisciplinary Text-to-Image Exam

September 18, 2025

Yu Qiao이 [arXiv]에 게시한 ‘GenExam: A Multidisciplinary Text-to-Image Exam’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research

September 17, 2025

Houquan Zhou이 [arXiv]에 게시한 ‘WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning

September 17, 2025

Huifeng Yin이 [arXiv]에 게시한 ‘WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents

September 17, 2025

Wenbiao Yin이 [arXiv]에 게시한 ‘WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Towards General Agentic Intelligence via Environment Scaling

September 17, 2025

Guangyu Li이 [arXiv]에 게시한 ‘Towards General Agentic Intelligence via Environment Scaling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Single-stream Policy Optimization

September 17, 2025

Zihan Ding이 [arXiv]에 게시한 ‘Single-stream Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Scaling Agents via Continual Pre-training

September 17, 2025

Guangyu Li이 [arXiv]에 게시한 ‘Scaling Agents via Continual Pre-training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization

September 17, 2025

Litu Ou이 [arXiv]에 게시한 ‘ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs

September 17, 2025

Luca Benini이 [arXiv]에 게시한 ‘Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis

September 17, 2025

Bo Liu이 [arXiv]에 게시한 ‘Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge

September 17, 2025

Wentao Zhang이 [arXiv]에 게시한 ‘Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation

September 17, 2025

Lixin Xu이 [arXiv]에 게시한 ‘Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Exact Coset Sampling for Quantum Lattice Algorithms

September 17, 2025

Yifan Zhang이 [arXiv]에 게시한 ‘Exact Coset Sampling for Quantum Lattice Algorithms’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving

September 17, 2025

Shansan Gong이 [arXiv]에 게시한 ‘EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 3D Aware Region Prompted Vision Language Model

September 17, 2025

Xiaolong Li이 [arXiv]에 게시한 ‘3D Aware Region Prompted Vision Language Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning

September 16, 2025

Yongliang Shen이 [arXiv]에 게시한 ‘UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation

September 16, 2025

Heshaam Faili이 [arXiv]에 게시한 ‘SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits

September 16, 2025

Zhenhao Chen이 [arXiv]에 게시한 ‘PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

September 16, 2025

Yang Zhou이 [arXiv]에 게시한 ‘OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Measuring Epistemic Humility in Multimodal Large Language Models

September 16, 2025

Kaiyang Zhou이 [arXiv]에 게시한 ‘Measuring Epistemic Humility in Multimodal Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Lost in Embeddings: Information Loss in Vision-Language Models

September 16, 2025

Ivan Vulić이 [arXiv]에 게시한 ‘Lost in Embeddings: Information Loss in Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models

September 16, 2025

Shuo Ren이 [arXiv]에 게시한 ‘Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Locality in Image Diffusion Models Emerges from Data Statistics

September 16, 2025

Vincent Sitzmann이 [arXiv]에 게시한 ‘Locality in Image Diffusion Models Emerges from Data Statistics’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting

September 16, 2025

Changlong Yu이 [arXiv]에 게시한 ‘Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence

September 16, 2025

Lionel M. Ni이 [arXiv]에 게시한 ‘LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts

September 16, 2025

Wenzhe Cai이 [arXiv]에 게시한 ‘InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings

September 16, 2025

Yixuan Tang이 [arXiv]에 게시한 ‘GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI

September 16, 2025

UVSKKR이 [arXiv]에 게시한 ‘EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding

September 16, 2025

Li Zheng이 [arXiv]에 게시한 ‘Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Groundi...

[논문리뷰] CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media

September 16, 2025

Subasish Das이 [arXiv]에 게시한 ‘CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] X-Part: high fidelity and structure coherent shape decomposition

September 15, 2025

Yunhan Yang이 [arXiv]에 게시한 ‘X-Part: high fidelity and structure coherent shape decomposition’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Virtual Agent Economies

September 15, 2025

William A. Cunningham이 [arXiv]에 게시한 ‘Virtual Agent Economies’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions

September 15, 2025

Dong Zhang이 [arXiv]에 게시한 ‘VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs

September 15, 2025

Jonas Geiping이 [arXiv]에 게시한 ‘The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading

September 15, 2025

Chenyu You이 [arXiv]에 게시한 ‘QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools

September 15, 2025

Xiaorui Wang이 [arXiv]에 게시한 ‘MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios

September 15, 2025

Bing Su이 [arXiv]에 게시한 ‘LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IntrEx: A Dataset for Modeling Engagement in Educational Conversations

September 15, 2025

Gabriele Pergola이 [arXiv]에 게시한 ‘IntrEx: A Dataset for Modeling Engagement in Educational Conversations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Inpainting-Guided Policy Optimization for Diffusion Large Language Models

September 15, 2025

Chenyu Wang이 [arXiv]에 게시한 ‘Inpainting-Guided Policy Optimization for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis

September 15, 2025

Song Guo이 [arXiv]에 게시한 ‘InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering

September 15, 2025

Zhehao Tan이 [arXiv]에 게시한 ‘HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies

September 15, 2025

Fabian Otto이 [arXiv]에 게시한 ‘FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China

September 15, 2025

XU Han이 [arXiv]에 게시한 ‘CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual Programmability: A Guide for Code-as-Thought in Chart Understanding

September 12, 2025

Ethan Chern이 [arXiv]에 게시한 ‘Visual Programmability: A Guide for Code-as-Thought in Chart Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

September 12, 2025

Zirui Ge이 [arXiv]에 게시한 ‘VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward

September 12, 2025

Xiaoyu Tan이 [arXiv]에 게시한 ‘The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward’ 논문에 대한...

[논문리뷰] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

September 12, 2025

Jian Gao이 [arXiv]에 게시한 ‘SpatialVID: A Large-Scale Video Dataset with Spatial Annotations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

September 12, 2025

Zhaohui Yang이 [arXiv]에 게시한 ‘SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated

September 12, 2025

Jamie Hayes이 [arXiv]에 게시한 ‘Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning

September 12, 2025

Yuzheng Zhuang이 [arXiv]에 게시한 ‘OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation

September 12, 2025

Dong-Ho Lee이 [arXiv]에 게시한 ‘Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering

September 12, 2025

Jianguo Zhang이 [arXiv]에 게시한 ‘LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis

September 12, 2025

Wentao Hu이 [arXiv]에 게시한 ‘Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

September 12, 2025

Zhuowei Chen이 [arXiv]에 게시한 ‘HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents

September 12, 2025

Xintao Wang이 [arXiv]에 게시한 ‘Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval

September 12, 2025

Kaicheng Yang이 [arXiv]에 게시한 ‘Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark

September 12, 2025

Shuai Bai이 [arXiv]에 게시한 ‘FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs

September 12, 2025

Kaiqi Kou이 [arXiv]에 게시한 ‘EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Can Understanding and Generation Truly Benefit Together – or Just Coexist?

September 12, 2025

Hui Han이 [arXiv]에 게시한 ‘Can Understanding and Generation Truly Benefit Together – or Just Coexist?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 2D Gaussian Splatting with Semantic Alignment for Image Inpainting

September 12, 2025

Guangming Lu이 [arXiv]에 게시한 ‘2D Gaussian Splatting with Semantic Alignment for Image Inpainting’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] So let's replace this phrase with insult... Lessons learned from generation of toxic texts with LLMs

September 11, 2025

Alexander Panchenko이 [arXiv]에 게시한 ‘ So let's replace this phrase with insult... Lessons learned from generation of toxic texts with LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RewardDance: Reward Scaling in Visual Generation

September 11, 2025

Liang Li이 [arXiv]에 게시한 ‘RewardDance: Reward Scaling in Visual Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] P3-SAM: Native 3D Part Segmentation

September 11, 2025

Yunhan Yang이 [arXiv]에 게시한 ‘P3-SAM: Native 3D Part Segmentation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Hunyuan-MT Technical Report

September 11, 2025

Yang Du이 [arXiv]에 게시한 ‘Hunyuan-MT Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants

September 11, 2025

Jacy Reese Anthis이 [arXiv]에 게시한 ‘HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EnvX: Agentize Everything with Agentic AI

September 11, 2025

Wenzheng Tom Tang이 [arXiv]에 게시한 ‘EnvX: Agentize Everything with Agentic AI’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning

September 11, 2025

Honglin Guo이 [arXiv]에 게시한 ‘AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Survey of Reinforcement Learning for Large Reasoning Models

September 11, 2025

Runze Liu이 [arXiv]에 게시한 ‘A Survey of Reinforcement Learning for Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 3D and 4D World Modeling: A Survey

September 11, 2025

Ao Liang이 [arXiv]에 게시한 ‘3D and 4D World Modeling: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ΔL Normalization: Rethink Loss Aggregation in RLVR

September 10, 2025

Lili Qiu이 [arXiv]에 게시한 ‘ΔL Normalization: Rethink Loss Aggregation in RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual Representation Alignment for Multimodal Large Language Models

September 10, 2025

Heeseong Shin이 [arXiv]에 게시한 ‘Visual Representation Alignment for Multimodal Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward

September 10, 2025

Fei Ding이 [arXiv]에 게시한 ‘UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding

September 10, 2025

Yongcheng Zeng이 [arXiv]에 게시한 ‘Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge

September 10, 2025

Dipanjan Das이 [arXiv]에 게시한 ‘SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reconstruction Alignment Improves Unified Multimodal Models

September 10, 2025

XuDong Wang이 [arXiv]에 게시한 ‘Reconstruction Alignment Improves Unified Multimodal Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling

September 10, 2025

Diana Marculescu이 [arXiv]에 게시한 ‘Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

September 10, 2025

Xinyu Yang이 [arXiv]에 게시한 ‘Parallel-R1: Towards Parallel Thinking via Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search

September 10, 2025

Tianjian Li이 [arXiv]에 게시한 ‘Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Language Self-Play For Data-Free Training

September 10, 2025

Vijai Mohan이 [arXiv]에 게시한 ‘Language Self-Play For Data-Free Training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions

September 10, 2025

Zherui Qiu이 [arXiv]에 게시한 ‘F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

September 10, 2025

Yingfang Zhang이 [arXiv]에 게시한 ‘Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Curia: A Multi-Modal Foundation Model for Radiology

September 10, 2025

Elodie Ferreres이 [arXiv]에 게시한 ‘Curia: A Multi-Modal Foundation Model for Radiology’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Causal Attention with Lookahead Keys

September 10, 2025

Quanquan Gu이 [arXiv]에 게시한 ‘Causal Attention with Lookahead Keys’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents

September 9, 2025

Aili Chen이 [arXiv]에 게시한 ‘WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UniVerse-1: Unified Audio-Video Generation via Stitching of Experts

September 9, 2025

Xinyao Liao이 [arXiv]에 게시한 ‘UniVerse-1: Unified Audio-Video Generation via Stitching of Experts’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet

September 9, 2025

See-Kiong Ng이 [arXiv]에 게시한 ‘Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers

September 9, 2025

Xia Xiao이 [arXiv]에 게시한 ‘Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem

September 9, 2025

Damien Sileo이 [arXiv]에 게시한 ‘Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World

September 9, 2025

Bowen Zhou이 [arXiv]에 게시한 ‘R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

September 9, 2025

Ke Shen이 [arXiv]에 게시한 ‘Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reverse-Engineered Reasoning for Open-Ended Generation

September 9, 2025

Wangchunshu Zhou이 [arXiv]에 게시한 ‘Reverse-Engineered Reasoning for Open-Ended Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforcement Learning Foundations for Deep Research Systems: A Survey

September 9, 2025

Wei Han이 [arXiv]에 게시한 ‘Reinforcement Learning Foundations for Deep Research Systems: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforced Visual Perception with Tools

September 9, 2025

Mingyang Fu이 [arXiv]에 게시한 ‘Reinforced Visual Perception with Tools’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents

September 9, 2025

James Zou이 [arXiv]에 게시한 ‘Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents

September 9, 2025

Zhengxi Lu이 [arXiv]에 게시한 ‘MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian

September 9, 2025

Hoi-Fong Mak이 [arXiv]에 게시한 ‘Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Interleaving Reasoning for Better Text-to-Image Generation

September 9, 2025

Shixiang Tang이 [arXiv]에 게시한 ‘Interleaving Reasoning for Better Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Focusing by Contrastive Attention: Enhancing VLMs’ Visual Reasoning

September 9, 2025

Baolong Bi이 [arXiv]에 게시한 ‘Focusing by Contrastive Attention: Enhancing VLMs’ Visual Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?

September 9, 2025

Rui Chen이 [arXiv]에 게시한 ‘Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Does DINOv3 Set a New Medical Vision Standard?

September 9, 2025

Bailiang Jian이 [arXiv]에 게시한 ‘Does DINOv3 Set a New Medical Vision Standard?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning

September 9, 2025

Dhanvin Sanjay Namboodiri이 [arXiv]에 게시한 ‘D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

September 8, 2025

Wenzheng Chang이 [arXiv]에 게시한 ‘WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning

September 8, 2025

Amit Namburi이 [arXiv]에 게시한 ‘WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Why Language Models Hallucinate

September 8, 2025

Edwin Zhang이 [arXiv]에 게시한 ‘Why Language Models Hallucinate’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] U-ARM : Ultra low-cost general teleoperation interface for robot manipulation

September 8, 2025

Junda Huang이 [arXiv]에 게시한 ‘U-ARM : Ultra low-cost general teleoperation interface for robot manipulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Symbolic Graphics Programming with Large Language Models

September 8, 2025

Kaipeng Zhang이 [arXiv]에 게시한 ‘Symbolic Graphics Programming with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Set Block Decoding is a Language Model Inference Accelerator

September 8, 2025

Jeremy Reizenstein이 [arXiv]에 게시한 ‘Set Block Decoding is a Language Model Inference Accelerator’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On Robustness and Reliability of Benchmark-Based Evaluation of LLMs

September 8, 2025

Kevin Roitero이 [arXiv]에 게시한 ‘On Robustness and Reliability of Benchmark-Based Evaluation of LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting

September 8, 2025

Vanessa Wildman이 [arXiv]에 게시한 ‘MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting’ 논...

[논문리뷰] LuxDiT: Lighting Estimation with Video Diffusion Transformer

September 8, 2025

Sanja Fidler이 [arXiv]에 게시한 ‘LuxDiT: Lighting Estimation with Video Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation

September 8, 2025

Zhan Zhao이 [arXiv]에 게시한 ‘LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Bootstrapping Task Spaces for Self-Improvement

September 8, 2025

Yoram Bachrach이 [arXiv]에 게시한 ‘Bootstrapping Task Spaces for Self-Improvement’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Behavioral Fingerprinting of Large Language Models

September 8, 2025

Xing Li이 [arXiv]에 게시한 ‘Behavioral Fingerprinting of Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding

September 5, 2025

Lionel Ni이 [arXiv]에 게시한 ‘Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Transition Models: Rethinking the Generative Learning Objective

September 5, 2025

Yangguang Li이 [arXiv]에 게시한 ‘Transition Models: Rethinking the Generative Learning Objective’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Towards a Unified View of Large Language Model Post-Training

September 5, 2025

Hongyi Liu이 [arXiv]에 게시한 ‘Towards a Unified View of Large Language Model Post-Training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings

September 5, 2025

Oren Glickman이 [arXiv]에 게시한 ‘NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?

September 5, 2025

Yu Fu이 [arXiv]에 게시한 ‘Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From Editor to Dense Geometry Estimator

September 5, 2025

Lang Nie이 [arXiv]에 게시한 ‘From Editor to Dense Geometry Estimator’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

September 5, 2025

Lingxi Xie이 [arXiv]에 게시한 ‘Few-step Flow for 3D Generation via Marginal-Data Transport Distillation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize

September 5, 2025

Muhao Chen이 [arXiv]에 게시한 ‘False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Durian: Dual Reference-guided Portrait Animation with Attribute Transfer

September 5, 2025

Hanbyul Joo이 [arXiv]에 게시한 ‘Durian: Dual Reference-guided Portrait Animation with Attribute Transfer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth

September 5, 2025

Chi-Li Chen이 [arXiv]에 게시한 ‘Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings

September 5, 2025

Meie Fang이 [arXiv]에 게시한 ‘Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Delta Activations: A Representation for Finetuned Large Language Models

September 5, 2025

Ser-Nam Lim이 [arXiv]에 게시한 ‘Delta Activations: A Representation for Finetuned Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks

September 5, 2025

Jiaxuan Lu이 [arXiv]에 게시한 ‘DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Robix: A Unified Model for Robot Interaction, Reasoning and Planning

September 4, 2025

Zixuan Wang이 [arXiv]에 게시한 ‘Robix: A Unified Model for Robot Interaction, Reasoning and Planning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Open Data Synthesis For Deep Research

September 4, 2025

Zheng Liu이 [arXiv]에 게시한 ‘Open Data Synthesis For Deep Research’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation

September 4, 2025

Kai Li이 [arXiv]에 게시한 ‘Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement

September 4, 2025

Hualiang Wang이 [arXiv]에 게시한 ‘MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations

September 4, 2025

Yoav Gur-Arieh이 [arXiv]에 게시한 ‘LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association

September 3, 2025

Daniel Cremers이 [arXiv]에 게시한 ‘ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use

September 3, 2025

Zhiheng Lyu이 [arXiv]에 게시한 ‘VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Universal Deep Research: Bring Your Own Model and Strategy

September 3, 2025

Pavlo Molchanov이 [arXiv]에 게시한 ‘Universal Deep Research: Bring Your Own Model and Strategy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

September 3, 2025

Haoyang Zou이 [arXiv]에 게시한 ‘UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views

September 3, 2025

Junchi Yan이 [arXiv]에 게시한 ‘Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Vie...

[논문리뷰] The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

September 3, 2025

Hejia Geng이 [arXiv]에 게시한 ‘The Landscape of Agentic Reinforcement Learning for LLMs: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang

September 3, 2025

Solomon Tsai이 [arXiv]에 게시한 ‘The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning

September 3, 2025

Qian Liu이 [arXiv]에 게시한 ‘SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction

September 3, 2025

bindsch이 [arXiv]에 게시한 ‘SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic

September 3, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion

September 3, 2025

Haicheng Wang이 [arXiv]에 게시한 ‘POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning

September 3, 2025

Zirui Wang이 [arXiv]에 게시한 ‘OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MobiAgent: A Systematic Framework for Customizable Mobile Agents

September 3, 2025

Wangbo Gong이 [arXiv]에 게시한 ‘MobiAgent: A Systematic Framework for Customizable Mobile Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Metis: Training Large Language Models with Advanced Low-Bit Quantization

September 3, 2025

Hengjie Cao이 [arXiv]에 게시한 ‘Metis: Training Large Language Models with Advanced Low-Bit Quantization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MedDINOv3: How to adapt vision foundation models for medical image segmentation?

September 3, 2025

Xiaofeng Yang이 [arXiv]에 게시한 ‘MedDINOv3: How to adapt vision foundation models for medical image segmentation?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision

September 3, 2025

Yan-Jie Zhou이 [arXiv]에 게시한 ‘M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

September 3, 2025

Jianwei Yang이 [arXiv]에 게시한 ‘LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Kwai Keye-VL 1.5 Technical Report

September 3, 2025

SXxtyz이 [arXiv]에 게시한 ‘Kwai Keye-VL 1.5 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Jointly Reinforcing Diversity and Quality in Language Model Generations

September 3, 2025

Tianlu이 [arXiv]에 게시한 ‘Jointly Reinforcing Diversity and Quality in Language Model Generations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Improving Large Vision and Language Models by Learning from a Panel of Peers

September 3, 2025

Simon Jenni이 [arXiv]에 게시한 ‘Improving Large Vision and Language Models by Learning from a Panel of Peers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR

September 3, 2025

Lu Wang이 [arXiv]에 게시한 ‘Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GenCompositor: Generative Video Compositing with Diffusion Transformer

September 3, 2025

Lingen Li이 [arXiv]에 게시한 ‘GenCompositor: Generative Video Compositing with Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games

September 3, 2025

Dongmin Park이 [arXiv]에 게시한 ‘FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models

September 3, 2025

Zhen Wang이 [arXiv]에 게시한 ‘FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Fantastic Pretraining Optimizers and Where to Find Them

September 3, 2025

Percy Liang이 [arXiv]에 게시한 ‘Fantastic Pretraining Optimizers and Where to Find Them’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding

September 3, 2025

Xuanyu Zheng이 [arXiv]에 게시한 ‘ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing

September 3, 2025

Amin Heyrani Nobar이 [arXiv]에 게시한 ‘Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DCPO: Dynamic Clipping Policy Optimization

September 3, 2025

Kai Lu이 [arXiv]에 게시한 ‘DCPO: Dynamic Clipping Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection

September 3, 2025

Vito Renó이 [arXiv]에 게시한 ‘C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Benchmarking Optimizers for Large Language Model Pretraining

September 3, 2025

mjaggi이 [arXiv]에 게시한 ‘Benchmarking Optimizers for Large Language Model Pretraining’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Baichuan-M2: Scaling Medical Capability with Large Verifier System

September 3, 2025

Jayok6이 [arXiv]에 게시한 ‘Baichuan-M2: Scaling Medical Capability with Large Verifier System’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation

September 3, 2025

Xiaolei Huang이 [arXiv]에 게시한 ‘Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation’ 논문에 대한 자...

[논문리뷰] AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models

September 3, 2025

Rahul Karthikeyan이 [arXiv]에 게시한 ‘AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Al...

[논문리뷰] UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat

September 2, 2025

Omartificial-Intelligence-Space이 [arXiv]에 게시한 ‘UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables

September 2, 2025

Yu Zhao이 [arXiv]에 게시한 ‘T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning

September 2, 2025

Yuewei Zhang이 [arXiv]에 게시한 ‘PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes

September 2, 2025

Danijel Skočaj이 [arXiv]에 게시한 ‘No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench

September 2, 2025

Jayanth Srinivasa이 [arXiv]에 게시한 ‘How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench’ 논문에 대한 자세한 리뷰입...

[논문리뷰] From reactive to cognitive: brain-inspired spatial intelligence for embodied agents

September 2, 2025

Songming Liu이 [arXiv]에 게시한 ‘From reactive to cognitive: brain-inspired spatial intelligence for embodied agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UItron: Foundational GUI Agent with Advanced Perception and Planning

September 1, 2025

Yufeng Zhong이 [arXiv]에 게시한 ‘UItron: Foundational GUI Agent with Advanced Perception and Planning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training

September 1, 2025

Jiyao Deng이 [arXiv]에 게시한 ‘TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models

September 1, 2025

Yifan Lu이 [arXiv]에 게시한 ‘Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis

September 1, 2025

Pengcheng Chen이 [arXiv]에 게시한 ‘TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning

September 1, 2025

Han Hu이 [arXiv]에 게시한 ‘R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Morae: Proactively Pausing UI Agents for User Choices

September 1, 2025

Amy Pavel이 [arXiv]에 게시한 ‘Morae: Proactively Pausing UI Agents for User Choices’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mimicking the Physicist’s Eye:A VLM-centric Approach for Physics Formula Discovery

September 1, 2025

Wenjie Zhou이 [arXiv]에 게시한 ‘Mimicking the Physicist’s Eye:A VLM-centric Approach for Physics Formula Discovery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation

September 1, 2025

Tianhai Liang이 [arXiv]에 게시한 ‘HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control

September 1, 2025

Zhaoqing Chen이 [arXiv]에 게시한 ‘EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Efficient Code Embeddings from Code Generation Models

September 1, 2025

Han Xiao이 [arXiv]에 게시한 ‘Efficient Code Embeddings from Code Generation Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation

September 1, 2025

Qi Jia이 [arXiv]에 게시한 ‘Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CLIPSym: Delving into Symmetry Detection with CLIP

September 1, 2025

Raymond A. Yeh이 [arXiv]에 게시한 ‘CLIPSym: Delving into Symmetry Detection with CLIP’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers

September 1, 2025

Jiamin Wu이 [arXiv]에 게시한 ‘A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AHELM: A Holistic Evaluation of Audio-Language Models

September 1, 2025

Siwei Yang이 [arXiv]에 게시한 ‘AHELM: A Holistic Evaluation of Audio-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code

September 1, 2025

Libo Chen이 [arXiv]에 게시한 ‘A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] rStar2-Agent: Agentic Reasoning Technical Report

August 29, 2025

Weijiang Xu이 [arXiv]에 게시한 ‘rStar2-Agent: Agentic Reasoning Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning

August 29, 2025

Jiahe Tian이 [arXiv]에 게시한 ‘USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection

August 29, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning

August 29, 2025

Simin Ma이 [arXiv]에 게시한 ‘TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ROSE: Remove Objects with Side Effects in Videos

August 29, 2025

Hantang Liu이 [arXiv]에 게시한 ‘ROSE: Remove Objects with Side Effects in Videos’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Provable Benefits of In-Tool Learning for Large Language Models

August 29, 2025

Vivien Cabannes이 [arXiv]에 게시한 ‘Provable Benefits of In-Tool Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

August 29, 2025

Jiazi Bu이 [arXiv]에 게시한 ‘Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD

August 29, 2025

Roy Ka-Wei Lee이 [arXiv]에 게시한 ‘Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning

August 29, 2025

Yitong Wang이 [arXiv]에 게시한 ‘OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models

August 29, 2025

Alex Endert이 [arXiv]에 게시한 ‘OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Multi-View 3D Point Tracking

August 29, 2025

Irem Demir이 [arXiv]에 게시한 ‘Multi-View 3D Point Tracking’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mixture of Contexts for Long Video Generation

August 29, 2025

Junfei Xiao이 [arXiv]에 게시한 ‘Mixture of Contexts for Long Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

August 29, 2025

Shashank Biju이 [arXiv]에 게시한 ‘MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FakeParts: a New Family of AI-Generated DeepFakes

August 29, 2025

Xi Wang이 [arXiv]에 게시한 ‘FakeParts: a New Family of AI-Generated DeepFakes’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Dress&Dance: Dress up and Dance as You Like It - Technical Preview

August 29, 2025

Yu-Xiong Wang이 [arXiv]에 게시한 ‘Dress&Dance: Dress up and Dance as You Like It - Technical Preview’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Collaborative Multi-Modal Coding for High-Quality 3D Generation

August 29, 2025

Ziwei Liu이 [arXiv]에 게시한 ‘Collaborative Multi-Modal Coding for High-Quality 3D Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification

August 29, 2025

Liqiang Nie이 [arXiv]에 게시한 ‘CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AWorld: Orchestrating the Training Recipe for Agentic AI

August 29, 2025

Qintong Wu이 [arXiv]에 게시한 ‘AWorld: Orchestrating the Training Recipe for Agentic AI’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference

August 28, 2025

Chunlei Han이 [arXiv]에 게시한 ‘Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] StepWiser: Stepwise Generative Judges for Wiser Reasoning

August 28, 2025

Olga Golovneva이 [arXiv]에 게시한 ‘StepWiser: Stepwise Generative Judges for Wiser Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Self-Rewarding Vision-Language Model via Reasoning Decomposition

August 28, 2025

Zhenwen Liang이 [arXiv]에 게시한 ‘Self-Rewarding Vision-Language Model via Reasoning Decomposition’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Predicting the Order of Upcoming Tokens Improves Language Modeling

August 28, 2025

Alham Fikri Aji이 [arXiv]에 게시한 ‘Predicting the Order of Upcoming Tokens Improves Language Modeling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment

August 28, 2025

An-An Liu이 [arXiv]에 게시한 ‘MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents

August 28, 2025

Yue Yao이 [arXiv]에 게시한 ‘Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation

August 28, 2025

Yan Zhou이 [arXiv]에 게시한 ‘MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Gaze into the Heart: A Multi-View Video Dataset for rPPG and Health Biomarkers Estimation

August 28, 2025

Anton Ivaschenko이 [arXiv]에 게시한 ‘Gaze into the Heart: A Multi-View Video Dataset for rPPG and Health Biomarkers Estimation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies

August 28, 2025

Sitong Mao이 [arXiv]에 게시한 ‘Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Diffusion Language Models Know the Answer Before Decoding

August 28, 2025

Shilin Yan이 [arXiv]에 게시한 ‘Diffusion Language Models Know the Answer Before Decoding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis

August 28, 2025

Ion Stoica이 [arXiv]에 게시한 ‘DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

August 28, 2025

Jianze Liang이 [arXiv]에 게시한 ‘CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning’ 논문에 대한 ...

[논문리뷰] Beyond Transcription: Mechanistic Interpretability in ASR

August 28, 2025

Aviv Shamsian이 [arXiv]에 게시한 ‘Beyond Transcription: Mechanistic Interpretability in ASR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AudioStory: Generating Long-Form Narrative Audio with Large Language Models

August 28, 2025

Yixiao Ge이 [arXiv]에 게시한 ‘AudioStory: Generating Long-Form Narrative Audio with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Wan-S2V: Audio-Driven Cinematic Video Generation

August 27, 2025

Chaonan Ji이 [arXiv]에 게시한 ‘Wan-S2V: Audio-Driven Cinematic Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space

August 27, 2025

Rui Chen이 [arXiv]에 게시한 ‘VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VibeVoice Technical Report

August 27, 2025

Yaoyao Chang이 [arXiv]에 게시한 ‘VibeVoice Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Unraveling the cognitive patterns of Large Language Models through module communities

August 27, 2025

Jianxi Gao이 [arXiv]에 게시한 ‘Unraveling the cognitive patterns of Large Language Models through module communities’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning

August 27, 2025

Ran Guo이 [arXiv]에 게시한 ‘UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling

August 27, 2025

Zhoufutu Wen이 [arXiv]에 게시한 ‘TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling’ 논문에 대한 ...

[논문리뷰] Training Language Model Agents to Find Vulnerabilities with CTF-Dojo

August 27, 2025

Zijian Wang이 [arXiv]에 게시한 ‘Training Language Model Agents to Find Vulnerabilities with CTF-Dojo’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models

August 27, 2025

Jiangjie Chen이 [arXiv]에 게시한 ‘ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Spacer: Towards Engineered Scientific Inspiration

August 27, 2025

zerojun48이 [arXiv]에 게시한 ‘Spacer: Towards Engineered Scientific Inspiration’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks

August 27, 2025

Kai Jia이 [arXiv]에 게시한 ‘ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting

August 27, 2025

Manuela Veloso이 [arXiv]에 게시한 ‘QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels

August 27, 2025

Dinesh Jayaraman이 [arXiv]에 게시한 ‘Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks

August 27, 2025

Daisuke Nohara이 [arXiv]에 게시한 ‘Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation

August 27, 2025

Jiaqi Yang이 [arXiv]에 게시한 ‘OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models

August 27, 2025

Beiqi Chen이 [arXiv]에 게시한 ‘ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MovieCORE: COgnitive REasoning in Movies

August 27, 2025

Hung-Ting Su이 [arXiv]에 게시한 ‘MovieCORE: COgnitive REasoning in Movies’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FastMesh:Efficient Artistic Mesh Generation via Component Decoupling

August 27, 2025

Xingang Pan이 [arXiv]에 게시한 ‘FastMesh:Efficient Artistic Mesh Generation via Component Decoupling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning

August 27, 2025

Arman Cohan이 [arXiv]에 게시한 ‘Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation

August 27, 2025

Kun Kuang이 [arXiv]에 게시한 ‘ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CineScale: Free Lunch in High-Resolution Cinematic Visual Generation

August 27, 2025

Ziwei Liu이 [arXiv]에 게시한 ‘CineScale: Free Lunch in High-Resolution Cinematic Visual Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics

August 27, 2025

Dongchen Huang이 [arXiv]에 게시한 ‘CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Autoregressive Universal Video Segmentation Model

August 27, 2025

Albert Gu이 [arXiv]에 게시한 ‘Autoregressive Universal Video Segmentation Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation

August 26, 2025

Haoxiang Shi이 [arXiv]에 게시한 ‘Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UQ: Assessing Language Models on Unsolved Questions

August 26, 2025

Wei Liu이 [arXiv]에 게시한 ‘UQ: Assessing Language Models on Unsolved Questions’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling

August 26, 2025

Jiaqi Li이 [arXiv]에 게시한 ‘TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation

August 26, 2025

Xihui Liu이 [arXiv]에 게시한 ‘T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SpotEdit: Evaluating Visually-Guided Image Editing Methods

August 26, 2025

Ersin Yumer이 [arXiv]에 게시한 ‘SpotEdit: Evaluating Visually-Guided Image Editing Methods’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ST-Raptor: LLM-Powered Semi-Structured Table Question Answering

August 26, 2025

Wei Zhou이 [arXiv]에 게시한 ‘ST-Raptor: LLM-Powered Semi-Structured Table Question Answering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs

August 26, 2025

Chenyu You이 [arXiv]에 게시한 ‘PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Neither Valid nor Reliable? Investigating the Use of LLMs as Judges

August 26, 2025

Golnoosh Farnadi이 [arXiv]에 게시한 ‘Neither Valid nor Reliable? Investigating the Use of LLMs as Judges’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting

August 26, 2025

Yanzhe Liang이 [arXiv]에 게시한 ‘MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MV-RAG: Retrieval Augmented Multiview Diffusion

August 26, 2025

sagiebenaim이 [arXiv]에 게시한 ‘MV-RAG: Retrieval Augmented Multiview Diffusion’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment

August 26, 2025

Doratossadat Dastgheib이 [arXiv]에 게시한 ‘MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Limitations of Normalization in Attention Mechanism

August 26, 2025

Radu State이 [arXiv]에 게시한 ‘Limitations of Normalization in Attention Mechanism’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

August 26, 2025

jinglinglin이 [arXiv]에 게시한 ‘InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German

August 26, 2025

Cristian-George Craciun이 [arXiv]에 게시한 ‘German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Explain Before You Answer: A Survey on Compositional Visual Reasoning

August 26, 2025

Xin Zheng이 [arXiv]에 게시한 ‘Explain Before You Answer: A Survey on Compositional Visual Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning

August 26, 2025

Jiale Zhao이 [arXiv]에 게시한 ‘Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling

August 26, 2025

Daniil Orel이 [arXiv]에 게시한 ‘Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Selective Contrastive Learning for Weakly Supervised Affordance Grounding

August 25, 2025

Jae-Pil Heo이 [arXiv]에 게시한 ‘Selective Contrastive Learning for Weakly Supervised Affordance Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics

August 25, 2025

Xiao Sun이 [arXiv]에 게시한 ‘Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts

August 25, 2025

Liming Fang이 [arXiv]에 게시한 ‘Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles

August 25, 2025

Diping Song이 [arXiv]에 게시한 ‘InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning

August 25, 2025

Pengcheng Qiu이 [arXiv]에 게시한 ‘End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EgoTwin: Dreaming Body and View in First Person

August 25, 2025

Wentao Wang이 [arXiv]에 게시한 ‘EgoTwin: Dreaming Body and View in First Person’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Do What? Teaching Vision-Language-Action Models to Reject the Impossible

August 25, 2025

Roei Herzig이 [arXiv]에 게시한 ‘Do What? Teaching Vision-Language-Action Models to Reject the Impossible’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CRISP: Persistent Concept Unlearning via Sparse Autoencoders

August 25, 2025

Yonatan Belinkov이 [arXiv]에 게시한 ‘CRISP: Persistent Concept Unlearning via Sparse Autoencoders’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning

August 25, 2025

Yulun Zhang이 [arXiv]에 게시한 ‘CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning’ 논문에 대한 자세한 리뷰...

[논문리뷰] Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

August 25, 2025

Ying Nian Wu이 [arXiv]에 게시한 ‘Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications

August 25, 2025

Liuyi Yao이 [arXiv]에 게시한 ‘AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions

August 25, 2025

Yidi Du이 [arXiv]에 게시한 ‘AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists

August 22, 2025

Heng Zhang이 [arXiv]에 게시한 ‘aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding

August 22, 2025

Rui Guo이 [arXiv]에 게시한 ‘When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Waver: Wave Your Way to Lifelike Video Generation

August 22, 2025

Yifu Zhang이 [arXiv]에 게시한 ‘Waver: Wave Your Way to Lifelike Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds

August 22, 2025

Chuiyun Wu이 [arXiv]에 게시한 ‘Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass

August 22, 2025

Ya Zhang이 [arXiv]에 게시한 ‘SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mobile-Agent-v3: Foundamental Agents for GUI Automation

August 22, 2025

Haowei Liu이 [arXiv]에 게시한 ‘Mobile-Agent-v3: Foundamental Agents for GUI Automation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries

August 22, 2025

huuuyeah이 [arXiv]에 게시한 ‘LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Intern-S1: A Scientific Multimodal Foundation Model

August 22, 2025

xuhuang87이 [arXiv]에 게시한 ‘Intern-S1: A Scientific Multimodal Foundation Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] INTIMA: A Benchmark for Human-AI Companionship Behavior

August 22, 2025

Yacine Jernite이 [arXiv]에 게시한 ‘INTIMA: A Benchmark for Human-AI Companionship Behavior’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models

August 22, 2025

Lifan Guo이 [arXiv]에 게시한 ‘Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Deep Think with Confidence

August 22, 2025

Xuewei Wang이 [arXiv]에 게시한 ‘Deep Think with Confidence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Survey on Large Language Model Benchmarks

August 22, 2025

Siyi Li이 [arXiv]에 게시한 ‘A Survey on Large Language Model Benchmarks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling

August 22, 2025

Shunsuke Saito이 [arXiv]에 게시한 ‘ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning

August 21, 2025

anoperson이 [arXiv]에 게시한 ‘mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?

August 21, 2025

Daeyoung Kim이 [arXiv]에 게시한 ‘ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Tinker: Diffusion’s Gift to 3D–Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization

August 21, 2025

Hao Chen이 [arXiv]에 게시한 ‘Tinker: Diffusion’s Gift to 3D–Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RynnEC: Bringing MLLMs into Embodied World

August 21, 2025

jiangpinliu이 [arXiv]에 게시한 ‘RynnEC: Bringing MLLMs into Embodied World’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation

August 21, 2025

Shiqing Wu이 [arXiv]에 게시한 ‘Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs

August 21, 2025

Haobo Xu이 [arXiv]에 게시한 ‘Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

August 21, 2025

Guoyin Wang이 [arXiv]에 게시한 ‘On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting’ 논문에 대한...

[논문리뷰] NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

August 21, 2025

abercovich이 [arXiv]에 게시한 ‘NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

August 21, 2025

Jiangmiao이 [arXiv]에 게시한 ‘MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers

August 21, 2025

Prathyusha Jwalapuram이 [arXiv]에 게시한 ‘MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer

August 21, 2025

Jeremiah Jiang이 [arXiv]에 게시한 ‘Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Leuvenshtein: Efficient FHE-based Edit Distance Computation with Single Bootstrap per Cell

August 21, 2025

Ingrid Verbauwhede이 [arXiv]에 게시한 ‘Leuvenshtein: Efficient FHE-based Edit Distance Computation with Single Bootstrap per Cell’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

August 21, 2025

tianlecai이 [arXiv]에 게시한 ‘FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models

August 21, 2025

Ziyan Kuang이 [arXiv]에 게시한 ‘From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery

August 21, 2025

zijieqiu이 [arXiv]에 게시한 ‘From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

August 21, 2025

Yu Lu이 [arXiv]에 게시한 ‘DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents

August 20, 2025

Flora D. Salim이 [arXiv]에 게시한 ‘ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer

August 20, 2025

Deyu Zhou이 [arXiv]에 게시한 ‘Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TempFlow-GRPO: When Timing Matters for GRPO in Flow Models

August 20, 2025

Jian Yang이 [arXiv]에 게시한 ‘TempFlow-GRPO: When Timing Matters for GRPO in Flow Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Semantic IDs for Joint Generative Search and Recommendation

August 20, 2025

Enrico Palumbo이 [arXiv]에 게시한 ‘Semantic IDs for Joint Generative Search and Recommendation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research

August 20, 2025

Susanne Schmidt이 [arXiv]에 게시한 ‘Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Prompt Orchestration Markup Language

August 20, 2025

Yuqing Yang이 [arXiv]에 게시한 ‘Prompt Orchestration Markup Language’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniTry: Virtual Try-On Anything without Masks

August 20, 2025

Xiaoduan Feng이 [arXiv]에 게시한 ‘OmniTry: Virtual Try-On Anything without Masks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MultiRef: Controllable Image Generation with Multiple Visual References

August 20, 2025

Shiyun Lang이 [arXiv]에 게시한 ‘MultiRef: Controllable Image Generation with Multiple Visual References’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence

August 20, 2025

Xin Chen이 [arXiv]에 게시한 ‘Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation

August 20, 2025

Xinyi Wang이 [arXiv]에 게시한 ‘Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation

August 20, 2025

Jonas Geiping이 [arXiv]에 게시한 ‘MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence

August 20, 2025

Fernando López이 [arXiv]에 게시한 ‘MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents

August 20, 2025

Jun Dong이 [arXiv]에 게시한 ‘MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

August 20, 2025

Yen-Yu Lin이 [arXiv]에 게시한 ‘LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Leveraging Large Language Models for Predictive Analysis of Human Misery

August 20, 2025

Abhilash Nandy이 [arXiv]에 게시한 ‘Leveraging Large Language Models for Predictive Analysis of Human Misery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge

August 20, 2025

Alice Wang이 [arXiv]에 게시한 ‘Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation

August 20, 2025

Fei Ni이 [arXiv]에 게시한 ‘Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations

August 20, 2025

Mounia Lalmas이 [arXiv]에 게시한 ‘Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Selection

August 20, 2025

Adriano Koshiyama이 [arXiv]에 게시한 ‘CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Select...

[논문리뷰] Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends

August 20, 2025

Xixiang Zhao이 [arXiv]에 게시한 ‘Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

August 20, 2025

Liam-Liu이 [arXiv]에 게시한 ‘Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CAMAR: Continuous Actions Multi-Agent Routing

August 20, 2025

Alexey Skrynnik이 [arXiv]에 게시한 ‘CAMAR: Continuous Actions Multi-Agent Routing’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Human Judgment: A Bayesian Evaluation of LLMs’ Moral Values Understanding

August 20, 2025

Alina Landowska이 [arXiv]에 게시한 ‘Beyond Human Judgment: A Bayesian Evaluation of LLMs’ Moral Values Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Advances in Speech Separation: Techniques, Challenges, and Future Trends

August 20, 2025

Zhuo Chen이 [arXiv]에 게시한 ‘Advances in Speech Separation: Techniques, Challenges, and Future Trends’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models

August 20, 2025

Zishang Jiang이 [arXiv]에 게시한 ‘A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs

August 19, 2025

Elena Tutubalina이 [arXiv]에 게시한 ‘When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Speed Always Wins: A Survey on Efficient Architectures for Large Language Models

August 19, 2025

Jusen Du이 [arXiv]에 게시한 ‘Speed Always Wins: A Survey on Efficient Architectures for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models

August 19, 2025

Meiqi Wu이 [arXiv]에 게시한 ‘S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Representing Speech Through Autoregressive Prediction of Cochlear Tokens

August 19, 2025

Daniel L. K. Yamins이 [arXiv]에 게시한 ‘Representing Speech Through Autoregressive Prediction of Cochlear Tokens’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforcement Learning with Rubric Anchors

August 19, 2025

Haokai Xu이 [arXiv]에 게시한 ‘Reinforcement Learning with Rubric Anchors’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Precise Action-to-Video Generation Through Visual Action Prompts

August 19, 2025

Minghan Qin이 [arXiv]에 게시한 ‘Precise Action-to-Video Generation Through Visual Action Prompts’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Ovis2.5 Technical Report

August 19, 2025

Yang Li이 [arXiv]에 게시한 ‘Ovis2.5 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Next Visual Granularity Generation

August 19, 2025

Kang Liao이 [arXiv]에 게시한 ‘Next Visual Granularity Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model

August 19, 2025

Yifan Zhang이 [arXiv]에 게시한 ‘Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models

August 19, 2025

Zixiang Gao이 [arXiv]에 게시한 ‘Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping

August 19, 2025

Tyler Derr이 [arXiv]에 게시한 ‘Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds

August 19, 2025

Artyom Sorokin이 [arXiv]에 게시한 ‘HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Has GPT-5 Achieved Spatial Intelligence? An Empirical Study

August 19, 2025

Ruisi Wang이 [arXiv]에 게시한 ‘Has GPT-5 Achieved Spatial Intelligence? An Empirical Study’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration

August 19, 2025

Evgeny Burnaev이 [arXiv]에 게시한 ‘G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning

August 19, 2025

Yufeng Wang이 [arXiv]에 게시한 ‘ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information

August 19, 2025

Xi Yang이 [arXiv]에 게시한 ‘Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 4DNeX: Feed-Forward 4D Generative Modeling Made Easy

August 19, 2025

Zeng Tao이 [arXiv]에 게시한 ‘4DNeX: Feed-Forward 4D Generative Modeling Made Easy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] X-Node: Self-Explanation is All We Need

August 18, 2025

Islem Rekik이 [arXiv]에 게시한 ‘X-Node: Self-Explanation is All We Need’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Thyme: Think Beyond Images

August 18, 2025

Wei Chen이 [arXiv]에 게시한 ‘Thyme: Think Beyond Images’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TexVerse: A Universe of 3D Objects with High-Resolution Textures

August 18, 2025

Nan Cao이 [arXiv]에 게시한 ‘TexVerse: A Universe of 3D Objects with High-Resolution Textures’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation

August 18, 2025

Junyong Noh이 [arXiv]에 게시한 ‘StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SSRL: Self-Search Reinforcement Learning

August 18, 2025

Yanxu Chen이 [arXiv]에 게시한 ‘SSRL: Self-Search Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation

August 18, 2025

Paolo Soda이 [arXiv]에 게시한 ‘SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing

August 18, 2025

Xianpei Han이 [arXiv]에 게시한 ‘PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data

August 18, 2025

Nicolas Gonthier이 [arXiv]에 게시한 ‘MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

August 18, 2025

Mu Xu이 [arXiv]에 게시한 ‘FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DINOv3

August 18, 2025

Maxime Oquab이 [arXiv]에 게시한 ‘DINOv3’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Controlling Multimodal LLMs via Reward-guided Decoding

August 18, 2025

Michal Drozdzal이 [arXiv]에 게시한 ‘Controlling Multimodal LLMs via Reward-guided Decoding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing

August 15, 2025

Gjergji Kasneci이 [arXiv]에 게시한 ‘When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in...

[논문리뷰] We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning

August 15, 2025

Xiaowan Wang이 [arXiv]에 게시한 ‘We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UI-Venus Technical Report: Building High-performance UI Agents with RFT

August 15, 2025

Shuheng Shen이 [arXiv]에 게시한 ‘UI-Venus Technical Report: Building High-performance UI Agents with RFT’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing

August 15, 2025

Xiaoyu Li이 [arXiv]에 게시한 ‘ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer

August 15, 2025

Honghua Chen이 [arXiv]에 게시한 ‘STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Processing and acquisition traces in visual encoders: What does CLIP know about your camera?

August 15, 2025

Giorgos Tolias이 [arXiv]에 게시한 ‘Processing and acquisition traces in visual encoders: What does CLIP know about your camera?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models

August 15, 2025

Qinghao Ye이 [arXiv]에 게시한 ‘Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts

August 15, 2025

Rui Lu이 [arXiv]에 게시한 ‘PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

August 15, 2025

Quan Sun이 [arXiv]에 게시한 ‘NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs

August 15, 2025

Yi Yuan이 [arXiv]에 게시한 ‘HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms

August 15, 2025

Ziyin Zhang이 [arXiv]에 게시한 ‘From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms’ 논문에 대한 자세한 ...

[논문리뷰] A Survey on Diffusion Language Models

August 15, 2025

Zhiqiang Shen이 [arXiv]에 게시한 ‘A Survey on Diffusion Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models

August 14, 2025

Dongdong Zhang이 [arXiv]에 게시한 ‘VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Story2Board: A Training-Free Approach for Expressive Storyboard Generation

August 14, 2025

Dani Lischinski이 [arXiv]에 게시한 ‘Story2Board: A Training-Free Approach for Expressive Storyboard Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation

August 14, 2025

Chen Li이 [arXiv]에 게시한 ‘Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory

August 14, 2025

Yuan Lin이 [arXiv]에 게시한 ‘Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models

August 14, 2025

Zeynep Akata이 [arXiv]에 게시한 ‘Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery

August 14, 2025

Di Zhang이 [arXiv]에 게시한 ‘Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models

August 14, 2025

Zhihan Zhou이 [arXiv]에 게시한 ‘MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models’ 논문에 대한 자세한 리뷰...

[논문리뷰] Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment

August 14, 2025

Lei Fan이 [arXiv]에 게시한 ‘Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding

August 14, 2025

Di Zhang이 [arXiv]에 게시한 ‘IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors

August 14, 2025

Qingnan Fan이 [arXiv]에 게시한 ‘GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation

August 14, 2025

Zhenghao Hu이 [arXiv]에 게시한 ‘Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing

August 14, 2025

Hao Zhang이 [arXiv]에 게시한 ‘Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models

August 14, 2025

Guiyang Hou이 [arXiv]에 게시한 ‘Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study

August 14, 2025

Gjergji Kasneci이 [arXiv]에 게시한 ‘Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving

August 14, 2025

Jinjie Gu이 [arXiv]에 게시한 ‘AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance

August 14, 2025

Yong Li이 [arXiv]에 게시한 ‘AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion

August 13, 2025

Rachid Nedjai이 [arXiv]에 게시한 ‘WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion’ 논문에 대...

[논문리뷰] VertexRegen: Mesh Generation with Continuous Level of Detail

August 13, 2025

Jakob Engel이 [arXiv]에 게시한 ‘VertexRegen: Mesh Generation with Continuous Level of Detail’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation

August 13, 2025

Kevin Galim이 [arXiv]에 게시한 ‘UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Train Long, Think Short: Curriculum Learning for Efficient Reasoning

August 13, 2025

Marzyeh Ghassemi이 [arXiv]에 게시한 ‘Train Long, Think Short: Curriculum Learning for Efficient Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors

August 13, 2025

Haoran Xu이 [arXiv]에 게시한 ‘Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation

August 13, 2025

Rachel Bawden이 [arXiv]에 게시한 ‘TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models

August 13, 2025

Chenchen Jing이 [arXiv]에 게시한 ‘Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Test-Time Reinforcement Learning for GUI Grounding via Region Consistency

August 13, 2025

Zhengxi Lu이 [arXiv]에 게시한 ‘Test-Time Reinforcement Learning for GUI Grounding via Region Consistency’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OpenCUA: Open Foundations for Computer-Use Agents

August 13, 2025

Tianbao Xie이 [arXiv]에 게시한 ‘OpenCUA: Open Foundations for Computer-Use Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations

August 13, 2025

Haoyue Zhan이 [arXiv]에 게시한 ‘NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Matrix-3D: Omnidirectional Explorable 3D World Generation

August 13, 2025

Yuqi Li이 [arXiv]에 게시한 ‘Matrix-3D: Omnidirectional Explorable 3D World Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches

August 13, 2025

Qiang Ju이 [arXiv]에 게시한 ‘HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay

August 13, 2025

Yang Fan이 [arXiv]에 게시한 ‘GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments

August 13, 2025

Xuesong Yao이 [arXiv]에 게시한 ‘Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy

August 13, 2025

Elizabeth Karpinski이 [arXiv]에 게시한 ‘Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition

August 13, 2025

Lukáš Burget이 [arXiv]에 게시한 ‘DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Cut2Next: Generating Next Shot via In-Context Tuning

August 13, 2025

Yu Qiao이 [arXiv]에 게시한 ‘Cut2Next: Generating Next Shot via In-Context Tuning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CharacterShot: Controllable and Consistent 4D Character Animation

August 13, 2025

Fei Shen이 [arXiv]에 게시한 ‘CharacterShot: Controllable and Consistent 4D Character Animation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mitigation on NISQ Hardware

August 13, 2025

Jhon Alejandro Andrade이 [arXiv]에 게시한 ‘Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mit...

[논문리뷰] BiasGym: Fantastic Biases and How to Find (and Remove) Them

August 13, 2025

Arnav Arora이 [arXiv]에 게시한 ‘BiasGym: Fantastic Biases and How to Find (and Remove) Them’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL

August 13, 2025

Chuyi He이 [arXiv]에 게시한 ‘Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators

August 13, 2025

Tao Zhang이 [arXiv]에 게시한 ‘AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Aryabhata: An exam-focused language model for JEE Math

August 13, 2025

Sandeep Varma이 [arXiv]에 게시한 ‘Aryabhata: An exam-focused language model for JEE Math’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Adversarial Video Promotion Against Text-to-Video Retrieval

August 13, 2025

Shuai Liu이 [arXiv]에 게시한 ‘Adversarial Video Promotion Against Text-to-Video Retrieval’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WideSearch: Benchmarking Agentic Broad Info-Seeking

August 12, 2025

Yan Gao이 [arXiv]에 게시한 ‘WideSearch: Benchmarking Agentic Broad Info-Seeking’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs

August 12, 2025

Dasol Choi이 [arXiv]에 게시한 ‘When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

August 12, 2025

Tong Yu이 [arXiv]에 게시한 ‘VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UserBench: An Interactive Gym Environment for User-Centric Agents

August 12, 2025

Jianguo Zhang이 [arXiv]에 게시한 ‘UserBench: An Interactive Gym Environment for User-Centric Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future

August 12, 2025

Qiufeng Wang이 [arXiv]에 게시한 ‘Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences

August 12, 2025

Matvey Skripkin이 [arXiv]에 게시한 ‘Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation

August 12, 2025

Hengtao Shen이 [arXiv]에 게시한 ‘Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforcement Learning in Vision: A Survey

August 12, 2025

Qingwei Meng이 [arXiv]에 게시한 ‘Reinforcement Learning in Vision: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability

August 12, 2025

Yuchen Li이 [arXiv]에 게시한 ‘ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning

August 12, 2025

Jiaheng Liu이 [arXiv]에 게시한 ‘Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks

August 12, 2025

Hongxing Li이 [arXiv]에 게시한 ‘OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation

August 12, 2025

Xiaokun Feng이 [arXiv]에 게시한 ‘Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MolmoAct: Action Reasoning Models that can Reason in Space

August 12, 2025

Shuo Liu이 [arXiv]에 게시한 ‘MolmoAct: Action Reasoning Models that can Reason in Space’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs

August 12, 2025

Jianguo Li이 [arXiv]에 게시한 ‘MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning

August 12, 2025

Baihong Yuan이 [arXiv]에 게시한 ‘Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization

August 12, 2025

Guanting Dong이 [arXiv]에 게시한 ‘Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts

August 12, 2025

Tieyuan Chen이 [arXiv]에 게시한 ‘Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GLiClass: Generalist Lightweight Model for Sequence Classification Tasks

August 12, 2025

Alexander Yavorskyi이 [arXiv]에 게시한 ‘GLiClass: Generalist Lightweight Model for Sequence Classification Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control

August 12, 2025

Hongyu Liu이 [arXiv]에 게시한 ‘Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System

August 12, 2025

Reynold Cheng이 [arXiv]에 게시한 ‘Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs

August 12, 2025

Robert Kirk이 [arXiv]에 게시한 ‘Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Compressing Chain-of-Thought in LLMs via Step Entropy

August 12, 2025

Zhijian Xu이 [arXiv]에 게시한 ‘Compressing Chain-of-Thought in LLMs via Step Entropy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

August 12, 2025

Kai Zou이 [arXiv]에 게시한 ‘BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents

August 12, 2025

Mohit Bansal이 [arXiv]에 게시한 ‘Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

August 12, 2025

Xinhao Yi이 [arXiv]에 게시한 ‘A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems’ 논문에 대한 자세...

[논문리뷰] Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off

August 11, 2025

jgkwak이 [arXiv]에 게시한 ‘Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding

August 11, 2025

Bingqi Chen이 [arXiv]에 게시한 ‘UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal

August 11, 2025

Chengcheng Wan이 [arXiv]에 게시한 ‘Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh

August 11, 2025

Yi Yang이 [arXiv]에 게시한 ‘MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Memp: Exploring Agent Procedural Memory

August 11, 2025

Shuofei Qiao이 [arXiv]에 게시한 ‘Memp: Exploring Agent Procedural Memory’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs

August 11, 2025

Guohang Yan이 [arXiv]에 게시한 ‘MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LightSwitch: Multi-view Relighting with Material-guided Diffusion

August 11, 2025

Shubham Tulsiani이 [arXiv]에 게시한 ‘LightSwitch: Multi-view Relighting with Material-guided Diffusion’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization

August 11, 2025

Pengxiang Li이 [arXiv]에 게시한 ‘InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

August 11, 2025

GLM-4. 5 Team이 [arXiv]에 게시한 ‘GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing

August 11, 2025

Przemysław Spurek이 [arXiv]에 게시한 ‘GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Adapting Vision-Language Models Without Labels: A Comprehensive Survey

August 11, 2025

Eleni Chatzi이 [arXiv]에 게시한 ‘Adapting Vision-Language Models Without Labels: A Comprehensive Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling

August 8, 2025

Ruolin Shen이 [arXiv]에 게시한 ‘Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling’ 논문에 대한 자세한 리뷰입...

[논문리뷰] StrandDesigner: Towards Practical Strand Generation with Sketch Guidance

August 8, 2025

Xiaobin Hu이 [arXiv]에 게시한 ‘StrandDesigner: Towards Practical Strand Generation with Sketch Guidance’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression

August 8, 2025

Yifei Ji이 [arXiv]에 게시한 ‘Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation

August 8, 2025

Jian Yang이 [arXiv]에 게시한 ‘RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation

August 8, 2025

Xiao Yu이 [arXiv]에 게시한 ‘REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] R-Zero: Self-Evolving Reasoning LLM from Zero Data

August 8, 2025

Zongxia Li이 [arXiv]에 게시한 ‘R-Zero: Self-Evolving Reasoning LLM from Zero Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction

August 8, 2025

Prajit Das이 [arXiv]에 게시한 ‘PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

August 8, 2025

Xinyu Ye이 [arXiv]에 게시한 ‘On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Marco-Voice Technical Report

August 8, 2025

Qingjuan Li이 [arXiv]에 게시한 ‘Marco-Voice Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes

August 8, 2025

Xudong Jiang이 [arXiv]에 게시한 ‘MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities

August 8, 2025

Zhijie Sang이 [arXiv]에 게시한 ‘InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations

August 8, 2025

Chirag Shah이 [arXiv]에 게시한 ‘I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations’ 논문에...

[논문리뷰] I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking

August 8, 2025

Chao Wang이 [arXiv]에 게시한 ‘I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis

August 8, 2025

Reshmi Ghosh이 [arXiv]에 게시한 ‘Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity

August 8, 2025

Zhibing Li이 [arXiv]에 게시한 ‘Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation

August 8, 2025

Shengcong Chen이 [arXiv]에 게시한 ‘Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Evaluating, Synthesizing, and Enhancing for Customer Support Conversation

August 8, 2025

Feng Chen이 [arXiv]에 게시한 ‘Evaluating, Synthesizing, and Enhancing for Customer Support Conversation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Don’t Overthink It: A Survey of Efficient R1-style Large Reasoning Models

August 8, 2025

Fangzhou Yao이 [arXiv]에 게시한 ‘Don’t Overthink It: A Survey of Efficient R1-style Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning

August 8, 2025

Ziming Wang이 [arXiv]에 게시한 ‘DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CoAct-1: Computer-using Agents with Coding as Actions

August 8, 2025

Taiwei Shi이 [arXiv]에 게시한 ‘CoAct-1: Computer-using Agents with Coding as Actions’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability

August 8, 2025

Yuan Wu이 [arXiv]에 게시한 ‘Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability’ 논문에 대...

[논문리뷰] Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?

August 8, 2025

Junjie Yang이 [arXiv]에 게시한 ‘Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Are Today’s LLMs Ready to Explain Well-Being Concepts?

August 8, 2025

Huan Liu이 [arXiv]에 게시한 ‘Are Today’s LLMs Ready to Explain Well-Being Concepts?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents

August 7, 2025

Xinyu Yang이 [arXiv]에 게시한 ‘Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning

August 7, 2025

Maksim Nekrashevich이 [arXiv]에 게시한 ‘Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models

August 7, 2025

Elisabetta Rocchetti이 [arXiv]에 게시한 ‘The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Sotopia-RL: Reward Design for Social Intelligence

August 7, 2025

Keyang Xuan이 [arXiv]에 게시한 ‘Sotopia-RL: Reward Design for Social Intelligence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering

August 7, 2025

Ambuj Mehrish이 [arXiv]에 게시한 ‘SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Sel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generation

August 7, 2025

Hao Huang이 [arXiv]에 게시한 ‘Sel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management

August 7, 2025

Yunxin Liu이 [arXiv]에 게시한 ‘Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience

August 7, 2025

Xiaoyi Dong이 [arXiv]에 게시한 ‘SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks

August 7, 2025

Haozhe Zhang이 [arXiv]에 게시한 ‘Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization

August 7, 2025

Kechi Zhang이 [arXiv]에 게시한 ‘RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization’ 논문에 대한 자세한 리뷰입...

[논문리뷰] Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference

August 7, 2025

Jiaying Wu이 [arXiv]에 게시한 ‘Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets

August 7, 2025

MaziyarPanahi이 [arXiv]에 게시한 ‘OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets’ 논문에 대한 자세한 ...

[논문리뷰] MiDashengLM: Efficient Audio Understanding with General Audio Captions

August 7, 2025

Yadong Niu이 [arXiv]에 게시한 ‘MiDashengLM: Efficient Audio Understanding with General Audio Captions’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following

August 7, 2025

Liang Xu이 [arXiv]에 게시한 ‘Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LeanK: Learnable K Cache Channel Pruning for Efficient Decoding

August 7, 2025

Yuqing Yang이 [arXiv]에 게시한 ‘LeanK: Learnable K Cache Channel Pruning for Efficient Decoding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LaTCoder: Converting Webpage Design to Code with Layout-as-Thought

August 7, 2025

Tianpeng Lv이 [arXiv]에 게시한 ‘LaTCoder: Converting Webpage Design to Code with Layout-as-Thought’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens

August 7, 2025

Zhen Tan이 [arXiv]에 게시한 ‘Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards

August 7, 2025

Ling-I Wu이 [arXiv]에 게시한 ‘IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IAUNet: Instance-Aware U-Net

August 7, 2025

Dmytro Fishman이 [arXiv]에 게시한 ‘IAUNet: Instance-Aware U-Net’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HPSv3: Towards Wide-Spectrum Human Preference Score

August 7, 2025

Hongsheng Li이 [arXiv]에 게시한 ‘HPSv3: Towards Wide-Spectrum Human Preference Score’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

August 7, 2025

Feng Zhao이 [arXiv]에 게시한 ‘Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success

August 7, 2025

Ruslan Rakhimov이 [arXiv]에 게시한 ‘Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success’ 논문에 대한 자세한 리뷰...

[논문리뷰] Efficient Agents: Building Effective Agents While Reducing Cost

August 7, 2025

Yue Hou이 [arXiv]에 게시한 ‘Efficient Agents: Building Effective Agents While Reducing Cost’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation

August 7, 2025

Dong Chen이 [arXiv]에 게시한 ‘EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework

August 7, 2025

Chao Liang이 [arXiv]에 게시한 ‘DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction

August 7, 2025

Donghyeon Lee이 [arXiv]에 게시한 ‘CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor

August 7, 2025

Jinbao Wang이 [arXiv]에 게시한 ‘C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Agent Lightning: Train ANY AI Agents with Reinforcement Learning

August 7, 2025

Zilong Wang이 [arXiv]에 게시한 ‘Agent Lightning: Train ANY AI Agents with Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding

August 7, 2025

Jianke Zhu이 [arXiv]에 게시한 ‘A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Tool-integrated Reinforcement Learning for Repo Deep Search

August 6, 2025

Yanzhen Zou이 [arXiv]에 게시한 ‘Tool-integrated Reinforcement Learning for Repo Deep Search’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TRACEALIGN – Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs

August 6, 2025

Aman Chadha이 [arXiv]에 게시한 ‘TRACEALIGN – Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation

August 6, 2025

Tianyidan Xie이 [arXiv]에 게시한 ‘Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

August 6, 2025

Fan Xia이 [arXiv]에 게시한 ‘Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Multi-human Interactive Talking Dataset

August 6, 2025

Mike Zheng Shou이 [arXiv]에 게시한 ‘Multi-human Interactive Talking Dataset’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation

August 6, 2025

Chenyang Si이 [arXiv]에 게시한 ‘LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?

August 6, 2025

Yaojie Lu이 [arXiv]에 게시한 ‘LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer

August 6, 2025

Shunyu Yao이 [arXiv]에 게시한 ‘LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction

August 6, 2025

Jui-Hui Chung이 [arXiv]에 게시한 ‘Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward

August 6, 2025

Songyang Gao이 [arXiv]에 게시한 ‘CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ChartCap: Mitigating Hallucination of Dense Chart Captioning

August 6, 2025

Gunhee Kim이 [arXiv]에 게시한 ‘ChartCap: Mitigating Hallucination of Dense Chart Captioning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search

August 6, 2025

Jiwei Li이 [arXiv]에 게시한 ‘CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization

August 6, 2025

Aman Chadha이 [arXiv]에 게시한 ‘AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization...

[논문리뷰] VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

August 5, 2025

Bin Jia이 [arXiv]에 게시한 ‘VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension

August 5, 2025

Liyan Xu이 [arXiv]에 게시한 ‘SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Lifelong Learning in Physical Embodied Systems

August 5, 2025

Junkun Hong이 [arXiv]에 게시한 ‘RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Lifelong Learning in Physical Embodied Systems’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Qwen-Image Technical Report

August 5, 2025

Kaiyuan Gao이 [arXiv]에 게시한 ‘Qwen-Image Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Personalized Safety Alignment for Text-to-Image Diffusion Models

August 5, 2025

Kaidong Yu이 [arXiv]에 게시한 ‘Personalized Safety Alignment for Text-to-Image Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report

August 5, 2025

Anu Vellore이 [arXiv]에 게시한 ‘Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation

August 5, 2025

Yang Tian이 [arXiv]에 게시한 ‘InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Exploitation Is All You Need… for Exploration

August 5, 2025

Jesse Roberts이 [arXiv]에 게시한 ‘Exploitation Is All You Need… for Exploration’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Cyber-Zero: Training Cybersecurity Agents without Runtime

August 5, 2025

Zijian Wang이 [arXiv]에 게시한 ‘Cyber-Zero: Training Cybersecurity Agents without Runtime’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CellForge: Agentic Design of Virtual Cell Models

August 5, 2025

Daniel Shao이 [arXiv]에 게시한 ‘CellForge: Agentic Design of Virtual Cell Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models’ Instruction Following

August 5, 2025

Jiaqing Liang이 [arXiv]에 게시한 ‘Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models’ Instruction Following’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks

August 5, 2025

Zhiwei Zhang이 [arXiv]에 게시한 ‘AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models

August 5, 2025

Zuxuan Wu이 [arXiv]에 게시한 ‘A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation

August 4, 2025

Long Chen이 [arXiv]에 게시한 ‘SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SWE-Exp: Experience-Driven Software Issue Resolution

August 4, 2025

Heng Lian이 [arXiv]에 게시한 ‘SWE-Exp: Experience-Driven Software Issue Resolution’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution

August 4, 2025

Heng Lian이 [arXiv]에 게시한 ‘SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PixNerd: Pixel Neural Field Diffusion

August 4, 2025

Limin Wang이 [arXiv]에 게시한 ‘PixNerd: Pixel Neural Field Diffusion’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Multimodal Referring Segmentation: A Survey

August 4, 2025

Zuxuan Wu이 [arXiv]에 게시한 ‘Multimodal Referring Segmentation: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges

August 4, 2025

Chengfei Lv이 [arXiv]에 게시한 ‘Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Investigating Hallucination in Conversations for Low Resource Languages

August 4, 2025

Fatemeh Jamshidi이 [arXiv]에 게시한 ‘Investigating Hallucination in Conversations for Low Resource Languages’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation

August 4, 2025

Jianjiang Feng이 [arXiv]에 게시한 ‘IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models

August 4, 2025

Jiaqi Wang이 [arXiv]에 게시한 ‘Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

August 4, 2025

Hao Tang이 [arXiv]에 게시한 ‘3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models

August 3, 2025

Kaixin Wang이 [arXiv]에 게시한 ‘villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] iLRM: An Iterative Large 3D Reconstruction Model

August 3, 2025

Abdelrahman Mohamed이 [arXiv]에 게시한 ‘iLRM: An Iterative Large 3D Reconstruction Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs

August 3, 2025

Jiasheng Tang이 [arXiv]에 게시한 ‘TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving

August 3, 2025

Zhicheng Jiang이 [arXiv]에 게시한 ‘Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents

August 3, 2025

Anji Liu이 [arXiv]에 게시한 ‘Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RecGPT Technical Report

August 3, 2025

Jian Wu이 [arXiv]에 게시한 ‘RecGPT Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Phi-Ground Tech Report: Advancing Perception in GUI Grounding

August 3, 2025

Kai Qiu이 [arXiv]에 게시한 ‘Phi-Ground Tech Report: Advancing Perception in GUI Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Persona Vectors: Monitoring and Controlling Character Traits in Language Models

August 3, 2025

Jack Lindsey이 [arXiv]에 게시한 ‘Persona Vectors: Monitoring and Controlling Character Traits in Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective

August 3, 2025

Eric C. Larson이 [arXiv]에 게시한 ‘On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NeRF Is a Valuable Assistant for 3D Gaussian Splatting

August 3, 2025

ZeSheng Wang이 [arXiv]에 게시한 ‘NeRF Is a Valuable Assistant for 3D Gaussian Splatting’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Flow Equivariant Recurrent Neural Networks

August 3, 2025

T. Anderson Keller이 [arXiv]에 게시한 ‘Flow Equivariant Recurrent Neural Networks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Enhanced Arabic Text Retrieval with Attentive Relevance Scoring

August 3, 2025

Abdenour Hadid이 [arXiv]에 게시한 ‘Enhanced Arabic Text Retrieval with Attentive Relevance Scoring’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Efficient Machine Unlearning via Influence Approximation

August 3, 2025

Enhong Chen이 [arXiv]에 게시한 ‘Efficient Machine Unlearning via Influence Approximation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations

August 3, 2025

Yiwen Guo이 [arXiv]에 게시한 ‘C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification

August 3, 2025

Abdelmalik Taleb-Ahmed이 [arXiv]에 게시한 ‘Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification’ 논문에 대한 ...

[논문리뷰] AgroBench: Vision-Language Model Benchmark in Agriculture

August 3, 2025

Yoshitaka Ushiku이 [arXiv]에 게시한 ‘AgroBench: Vision-Language Model Benchmark in Agriculture’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reinforcement Learning

[논문리뷰] Reinforcement Learning on Pre-Training Data

September 24, 2025

Evander Yang이 [arXiv]에 게시한 ‘Reinforcement Learning on Pre-Training Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MAPO: Mixed Advantage Policy Optimization

September 24, 2025

Xuankun Rong이 [arXiv]에 게시한 ‘MAPO: Mixed Advantage Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery

September 23, 2025

Shiya Huang이 [arXiv]에 게시한 ‘VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

September 23, 2025

Shaohui Jiao이 [arXiv]에 게시한 ‘TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning

September 23, 2025

Damien Sileo이 [arXiv]에 게시한 ‘Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mano Report

September 23, 2025

Minghui Wu이 [arXiv]에 게시한 ‘Mano Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token’s Nature

September 23, 2025

Bin Cui이 [arXiv]에 게시한 ‘From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token’s Nature’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

September 23, 2025

Qinsheng Zhang이 [arXiv]에 게시한 ‘DiffusionNFT: Online Diffusion Reinforcement with Forward Process’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ARE: Scaling Up Agent Environments and Evaluations

September 23, 2025

Matteo Bettini이 [arXiv]에 게시한 ‘ARE: Scaling Up Agent Environments and Evaluations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent

September 22, 2025

Jiahui Yang이 [arXiv]에 게시한 ‘BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RecoWorld: Building Simulated Environments for Agentic Recommender Systems

September 19, 2025

Mingyuan Wu이 [arXiv]에 게시한 ‘RecoWorld: Building Simulated Environments for Agentic Recommender Systems’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FlowRL: Matching Reward Distributions for LLM Reasoning

September 19, 2025

Hengli Li이 [arXiv]에 게시한 ‘FlowRL: Matching Reward Distributions for LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning

September 18, 2025

Yicheng Pan이 [arXiv]에 게시한 ‘THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SAIL-VL2 Technical Report

September 18, 2025

Zijian Kang이 [arXiv]에 게시한 ‘SAIL-VL2 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning

September 17, 2025

Huifeng Yin이 [arXiv]에 게시한 ‘WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Single-stream Policy Optimization

September 17, 2025

Zihan Ding이 [arXiv]에 게시한 ‘Single-stream Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization

September 17, 2025

Litu Ou이 [arXiv]에 게시한 ‘ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving

September 17, 2025

Shansan Gong이 [arXiv]에 게시한 ‘EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning

September 16, 2025

Yongliang Shen이 [arXiv]에 게시한 ‘UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models

September 16, 2025

Shuo Ren이 [arXiv]에 게시한 ‘Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Inpainting-Guided Policy Optimization for Diffusion Large Language Models

September 15, 2025

Chenyu Wang이 [arXiv]에 게시한 ‘Inpainting-Guided Policy Optimization for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward

September 12, 2025

Xiaoyu Tan이 [arXiv]에 게시한 ‘The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward’ 논문에 대한...

[논문리뷰] Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents

September 12, 2025

Xintao Wang이 [arXiv]에 게시한 ‘Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Can Understanding and Generation Truly Benefit Together – or Just Coexist?

September 12, 2025

Hui Han이 [arXiv]에 게시한 ‘Can Understanding and Generation Truly Benefit Together – or Just Coexist?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Hunyuan-MT Technical Report

September 11, 2025

Yang Du이 [arXiv]에 게시한 ‘Hunyuan-MT Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning

September 11, 2025

Honglin Guo이 [arXiv]에 게시한 ‘AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Survey of Reinforcement Learning for Large Reasoning Models

September 11, 2025

Runze Liu이 [arXiv]에 게시한 ‘A Survey of Reinforcement Learning for Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ΔL Normalization: Rethink Loss Aggregation in RLVR

September 10, 2025

Lili Qiu이 [arXiv]에 게시한 ‘ΔL Normalization: Rethink Loss Aggregation in RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward

September 10, 2025

Fei Ding이 [arXiv]에 게시한 ‘UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

September 10, 2025

Xinyu Yang이 [arXiv]에 게시한 ‘Parallel-R1: Towards Parallel Thinking via Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search

September 10, 2025

Tianjian Li이 [arXiv]에 게시한 ‘Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Language Self-Play For Data-Free Training

September 10, 2025

Vijai Mohan이 [arXiv]에 게시한 ‘Language Self-Play For Data-Free Training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

September 10, 2025

Yingfang Zhang이 [arXiv]에 게시한 ‘Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

September 9, 2025

Ke Shen이 [arXiv]에 게시한 ‘Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforcement Learning Foundations for Deep Research Systems: A Survey

September 9, 2025

Wei Han이 [arXiv]에 게시한 ‘Reinforcement Learning Foundations for Deep Research Systems: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforced Visual Perception with Tools

September 9, 2025

Mingyang Fu이 [arXiv]에 게시한 ‘Reinforced Visual Perception with Tools’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Symbolic Graphics Programming with Large Language Models

September 8, 2025

Kaipeng Zhang이 [arXiv]에 게시한 ‘Symbolic Graphics Programming with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding

September 5, 2025

Lionel Ni이 [arXiv]에 게시한 ‘Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Open Data Synthesis For Deep Research

September 4, 2025

Zheng Liu이 [arXiv]에 게시한 ‘Open Data Synthesis For Deep Research’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

September 3, 2025

Haoyang Zou이 [arXiv]에 게시한 ‘UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning

September 3, 2025

Qian Liu이 [arXiv]에 게시한 ‘SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic

September 3, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MobiAgent: A Systematic Framework for Customizable Mobile Agents

September 3, 2025

Wangbo Gong이 [arXiv]에 게시한 ‘MobiAgent: A Systematic Framework for Customizable Mobile Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Kwai Keye-VL 1.5 Technical Report

September 3, 2025

SXxtyz이 [arXiv]에 게시한 ‘Kwai Keye-VL 1.5 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Jointly Reinforcing Diversity and Quality in Language Model Generations

September 3, 2025

Tianlu이 [arXiv]에 게시한 ‘Jointly Reinforcing Diversity and Quality in Language Model Generations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DCPO: Dynamic Clipping Policy Optimization

September 3, 2025

Kai Lu이 [arXiv]에 게시한 ‘DCPO: Dynamic Clipping Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Baichuan-M2: Scaling Medical Capability with Large Verifier System

September 3, 2025

Jayok6이 [arXiv]에 게시한 ‘Baichuan-M2: Scaling Medical Capability with Large Verifier System’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning

September 2, 2025

Yuewei Zhang이 [arXiv]에 게시한 ‘PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UItron: Foundational GUI Agent with Advanced Perception and Planning

September 1, 2025

Yufeng Zhong이 [arXiv]에 게시한 ‘UItron: Foundational GUI Agent with Advanced Perception and Planning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models

September 1, 2025

Yifan Lu이 [arXiv]에 게시한 ‘Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mimicking the Physicist’s Eye:A VLM-centric Approach for Physics Formula Discovery

September 1, 2025

Wenjie Zhou이 [arXiv]에 게시한 ‘Mimicking the Physicist’s Eye:A VLM-centric Approach for Physics Formula Discovery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation

September 1, 2025

Tianhai Liang이 [arXiv]에 게시한 ‘HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

August 29, 2025

Jiazi Bu이 [arXiv]에 게시한 ‘Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning

August 29, 2025

Yitong Wang이 [arXiv]에 게시한 ‘OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AWorld: Orchestrating the Training Recipe for Agentic AI

August 29, 2025

Qintong Wu이 [arXiv]에 게시한 ‘AWorld: Orchestrating the Training Recipe for Agentic AI’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] StepWiser: Stepwise Generative Judges for Wiser Reasoning

August 28, 2025

Olga Golovneva이 [arXiv]에 게시한 ‘StepWiser: Stepwise Generative Judges for Wiser Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Self-Rewarding Vision-Language Model via Reasoning Decomposition

August 28, 2025

Zhenwen Liang이 [arXiv]에 게시한 ‘Self-Rewarding Vision-Language Model via Reasoning Decomposition’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies

August 28, 2025

Sitong Mao이 [arXiv]에 게시한 ‘Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

August 28, 2025

Jianze Liang이 [arXiv]에 게시한 ‘CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning’ 논문에 대한 ...

[논문리뷰] TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling

August 27, 2025

Zhoufutu Wen이 [arXiv]에 게시한 ‘TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling’ 논문에 대한 ...

[논문리뷰] ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models

August 27, 2025

Jiangjie Chen이 [arXiv]에 게시한 ‘ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation

August 26, 2025

Haoxiang Shi이 [arXiv]에 게시한 ‘Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

August 26, 2025

jinglinglin이 [arXiv]에 게시한 ‘InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning

August 26, 2025

Jiale Zhao이 [arXiv]에 게시한 ‘Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling

August 26, 2025

Daniil Orel이 [arXiv]에 게시한 ‘Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning

August 25, 2025

Pengcheng Qiu이 [arXiv]에 게시한 ‘End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning

August 25, 2025

Yulun Zhang이 [arXiv]에 게시한 ‘CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning’ 논문에 대한 자세한 리뷰...

[논문리뷰] Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

August 25, 2025

Ying Nian Wu이 [arXiv]에 게시한 ‘Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mobile-Agent-v3: Foundamental Agents for GUI Automation

August 22, 2025

Haowei Liu이 [arXiv]에 게시한 ‘Mobile-Agent-v3: Foundamental Agents for GUI Automation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Intern-S1: A Scientific Multimodal Foundation Model

August 22, 2025

xuhuang87이 [arXiv]에 게시한 ‘Intern-S1: A Scientific Multimodal Foundation Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

August 21, 2025

Guoyin Wang이 [arXiv]에 게시한 ‘On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting’ 논문에 대한...

[논문리뷰] TempFlow-GRPO: When Timing Matters for GRPO in Flow Models

August 20, 2025

Jian Yang이 [arXiv]에 게시한 ‘TempFlow-GRPO: When Timing Matters for GRPO in Flow Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation

August 20, 2025

Fei Ni이 [arXiv]에 게시한 ‘Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models

August 20, 2025

Zishang Jiang이 [arXiv]에 게시한 ‘A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforcement Learning with Rubric Anchors

August 19, 2025

Haokai Xu이 [arXiv]에 게시한 ‘Reinforcement Learning with Rubric Anchors’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Thyme: Think Beyond Images

August 18, 2025

Wei Chen이 [arXiv]에 게시한 ‘Thyme: Think Beyond Images’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SSRL: Self-Search Reinforcement Learning

August 18, 2025

Yanxu Chen이 [arXiv]에 게시한 ‘SSRL: Self-Search Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning

August 15, 2025

Xiaowan Wang이 [arXiv]에 게시한 ‘We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models

August 15, 2025

Qinghao Ye이 [arXiv]에 게시한 ‘Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs

August 15, 2025

Yi Yuan이 [arXiv]에 게시한 ‘HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory

August 14, 2025

Yuan Lin이 [arXiv]에 게시한 ‘Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery

August 14, 2025

Di Zhang이 [arXiv]에 게시한 ‘Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models

August 14, 2025

Guiyang Hou이 [arXiv]에 게시한 ‘Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance

August 14, 2025

Yong Li이 [arXiv]에 게시한 ‘AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Train Long, Think Short: Curriculum Learning for Efficient Reasoning

August 13, 2025

Marzyeh Ghassemi이 [arXiv]에 게시한 ‘Train Long, Think Short: Curriculum Learning for Efficient Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors

August 13, 2025

Haoran Xu이 [arXiv]에 게시한 ‘Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models

August 13, 2025

Chenchen Jing이 [arXiv]에 게시한 ‘Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Test-Time Reinforcement Learning for GUI Grounding via Region Consistency

August 13, 2025

Zhengxi Lu이 [arXiv]에 게시한 ‘Test-Time Reinforcement Learning for GUI Grounding via Region Consistency’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL

August 13, 2025

Chuyi He이 [arXiv]에 게시한 ‘Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Aryabhata: An exam-focused language model for JEE Math

August 13, 2025

Sandeep Varma이 [arXiv]에 게시한 ‘Aryabhata: An exam-focused language model for JEE Math’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs

August 12, 2025

Dasol Choi이 [arXiv]에 게시한 ‘When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability

August 12, 2025

Yuchen Li이 [arXiv]에 게시한 ‘ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning

August 12, 2025

Jiaheng Liu이 [arXiv]에 게시한 ‘Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization

August 12, 2025

Guanting Dong이 [arXiv]에 게시한 ‘Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Compressing Chain-of-Thought in LLMs via Step Entropy

August 12, 2025

Zhijian Xu이 [arXiv]에 게시한 ‘Compressing Chain-of-Thought in LLMs via Step Entropy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding

August 11, 2025

Bingqi Chen이 [arXiv]에 게시한 ‘UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization

August 11, 2025

Pengxiang Li이 [arXiv]에 게시한 ‘InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

August 11, 2025

GLM-4. 5 Team이 [arXiv]에 게시한 ‘GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] R-Zero: Self-Evolving Reasoning LLM from Zero Data

August 8, 2025

Zongxia Li이 [arXiv]에 게시한 ‘R-Zero: Self-Evolving Reasoning LLM from Zero Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning

August 7, 2025

Maksim Nekrashevich이 [arXiv]에 게시한 ‘Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Sotopia-RL: Reward Design for Social Intelligence

August 7, 2025

Keyang Xuan이 [arXiv]에 게시한 ‘Sotopia-RL: Reward Design for Social Intelligence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience

August 7, 2025

Xiaoyi Dong이 [arXiv]에 게시한 ‘SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks

August 7, 2025

Haozhe Zhang이 [arXiv]에 게시한 ‘Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization

August 7, 2025

Kechi Zhang이 [arXiv]에 게시한 ‘RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization’ 논문에 대한 자세한 리뷰입...

[논문리뷰] Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following

August 7, 2025

Liang Xu이 [arXiv]에 게시한 ‘Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards

August 7, 2025

Ling-I Wu이 [arXiv]에 게시한 ‘IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success

August 7, 2025

Ruslan Rakhimov이 [arXiv]에 게시한 ‘Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success’ 논문에 대한 자세한 리뷰...

[논문리뷰] Agent Lightning: Train ANY AI Agents with Reinforcement Learning

August 7, 2025

Zilong Wang이 [arXiv]에 게시한 ‘Agent Lightning: Train ANY AI Agents with Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction

August 6, 2025

Jui-Hui Chung이 [arXiv]에 게시한 ‘Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward

August 6, 2025

Songyang Gao이 [arXiv]에 게시한 ‘CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search

August 6, 2025

Jiwei Li이 [arXiv]에 게시한 ‘CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Qwen-Image Technical Report

August 5, 2025

Kaiyuan Gao이 [arXiv]에 게시한 ‘Qwen-Image Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Exploitation Is All You Need… for Exploration

August 5, 2025

Jesse Roberts이 [arXiv]에 게시한 ‘Exploitation Is All You Need… for Exploration’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models

August 5, 2025

Zuxuan Wu이 [arXiv]에 게시한 ‘A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

August 4, 2025

Hao Tang이 [arXiv]에 게시한 ‘3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving

August 3, 2025

Zhicheng Jiang이 [arXiv]에 게시한 ‘Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents

August 3, 2025

Anji Liu이 [arXiv]에 게시한 ‘Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Large Language Models

[논문리뷰] Reinforcement Learning on Pre-Training Data

September 24, 2025

Evander Yang이 [arXiv]에 게시한 ‘Reinforcement Learning on Pre-Training Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Large Language Models Discriminate Against Speakers of German Dialects

September 24, 2025

Katharina von der Wense이 [arXiv]에 게시한 ‘Large Language Models Discriminate Against Speakers of German Dialects’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

September 23, 2025

Fatma Betül Terzioğlu이 [arXiv]에 게시한 ‘Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning

September 23, 2025

Zhaopeng Tu이 [arXiv]에 게시한 ‘SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LIMI: Less is More for Agency

September 23, 2025

happyZYM이 [arXiv]에 게시한 ‘LIMI: Less is More for Agency’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultural Text Adaptation in Indian Context

September 23, 2025

Maunendra Sankar Desarkar이 [arXiv]에 게시한 ‘DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultur...

[논문리뷰] AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?

September 23, 2025

Jaeho Lee이 [arXiv]에 게시한 ‘AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FlowRL: Matching Reward Distributions for LLM Reasoning

September 19, 2025

Hengli Li이 [arXiv]에 게시한 ‘FlowRL: Matching Reward Distributions for LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning

September 18, 2025

Yicheng Pan이 [arXiv]에 게시한 ‘THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale

September 18, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Towards General Agentic Intelligence via Environment Scaling

September 17, 2025

Guangyu Li이 [arXiv]에 게시한 ‘Towards General Agentic Intelligence via Environment Scaling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge

September 17, 2025

Wentao Zhang이 [arXiv]에 게시한 ‘Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning

September 16, 2025

Yongliang Shen이 [arXiv]에 게시한 ‘UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI

September 16, 2025

UVSKKR이 [arXiv]에 게시한 ‘EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs

September 15, 2025

Jonas Geiping이 [arXiv]에 게시한 ‘The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading

September 15, 2025

Chenyu You이 [arXiv]에 게시한 ‘QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge

September 10, 2025

Dipanjan Das이 [arXiv]에 게시한 ‘SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

September 10, 2025

Xinyu Yang이 [arXiv]에 게시한 ‘Parallel-R1: Towards Parallel Thinking via Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Language Self-Play For Data-Free Training

September 10, 2025

Vijai Mohan이 [arXiv]에 게시한 ‘Language Self-Play For Data-Free Training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet

September 9, 2025

See-Kiong Ng이 [arXiv]에 게시한 ‘Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

September 9, 2025

Ke Shen이 [arXiv]에 게시한 ‘Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Symbolic Graphics Programming with Large Language Models

September 8, 2025

Kaipeng Zhang이 [arXiv]에 게시한 ‘Symbolic Graphics Programming with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Behavioral Fingerprinting of Large Language Models

September 8, 2025

Xing Li이 [arXiv]에 게시한 ‘Behavioral Fingerprinting of Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth

September 5, 2025

Chi-Li Chen이 [arXiv]에 게시한 ‘Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Open Data Synthesis For Deep Research

September 4, 2025

Zheng Liu이 [arXiv]에 게시한 ‘Open Data Synthesis For Deep Research’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use

September 3, 2025

Zhiheng Lyu이 [arXiv]에 게시한 ‘VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

September 3, 2025

Hejia Geng이 [arXiv]에 게시한 ‘The Landscape of Agentic Reinforcement Learning for LLMs: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning

September 3, 2025

Qian Liu이 [arXiv]에 게시한 ‘SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction

September 3, 2025

bindsch이 [arXiv]에 게시한 ‘SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning

September 3, 2025

Zirui Wang이 [arXiv]에 게시한 ‘OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR

September 3, 2025

Lu Wang이 [arXiv]에 게시한 ‘Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Fantastic Pretraining Optimizers and Where to Find Them

September 3, 2025

Percy Liang이 [arXiv]에 게시한 ‘Fantastic Pretraining Optimizers and Where to Find Them’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models

September 3, 2025

Rahul Karthikeyan이 [arXiv]에 게시한 ‘AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Al...

[논문리뷰] Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models

September 1, 2025

Yifan Lu이 [arXiv]에 게시한 ‘Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning

August 29, 2025

Simin Ma이 [arXiv]에 게시한 ‘TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Provable Benefits of In-Tool Learning for Large Language Models

August 29, 2025

Vivien Cabannes이 [arXiv]에 게시한 ‘Provable Benefits of In-Tool Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Predicting the Order of Upcoming Tokens Improves Language Modeling

August 28, 2025

Alham Fikri Aji이 [arXiv]에 게시한 ‘Predicting the Order of Upcoming Tokens Improves Language Modeling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AudioStory: Generating Long-Form Narrative Audio with Large Language Models

August 28, 2025

Yixiao Ge이 [arXiv]에 게시한 ‘AudioStory: Generating Long-Form Narrative Audio with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Unraveling the cognitive patterns of Large Language Models through module communities

August 27, 2025

Jianxi Gao이 [arXiv]에 게시한 ‘Unraveling the cognitive patterns of Large Language Models through module communities’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling

August 27, 2025

Zhoufutu Wen이 [arXiv]에 게시한 ‘TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling’ 논문에 대한 ...

[논문리뷰] QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting

August 27, 2025

Manuela Veloso이 [arXiv]에 게시한 ‘QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks

August 27, 2025

Daisuke Nohara이 [arXiv]에 게시한 ‘Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning

August 27, 2025

Arman Cohan이 [arXiv]에 게시한 ‘Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation

August 27, 2025

Kun Kuang이 [arXiv]에 게시한 ‘ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics

August 27, 2025

Dongchen Huang이 [arXiv]에 게시한 ‘CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Explain Before You Answer: A Survey on Compositional Visual Reasoning

August 26, 2025

Xin Zheng이 [arXiv]에 게시한 ‘Explain Before You Answer: A Survey on Compositional Visual Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning

August 26, 2025

Jiale Zhao이 [arXiv]에 게시한 ‘Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning

August 25, 2025

Pengcheng Qiu이 [arXiv]에 게시한 ‘End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

August 25, 2025

Ying Nian Wu이 [arXiv]에 게시한 ‘Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mobile-Agent-v3: Foundamental Agents for GUI Automation

August 22, 2025

Haowei Liu이 [arXiv]에 게시한 ‘Mobile-Agent-v3: Foundamental Agents for GUI Automation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models

August 22, 2025

Lifan Guo이 [arXiv]에 게시한 ‘Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs

August 21, 2025

Haobo Xu이 [arXiv]에 게시한 ‘Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

August 21, 2025

Guoyin Wang이 [arXiv]에 게시한 ‘On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting’ 논문에 대한...

[논문리뷰] MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers

August 21, 2025

Prathyusha Jwalapuram이 [arXiv]에 게시한 ‘MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery

August 21, 2025

zijieqiu이 [arXiv]에 게시한 ‘From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Prompt Orchestration Markup Language

August 20, 2025

Yuqing Yang이 [arXiv]에 게시한 ‘Prompt Orchestration Markup Language’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Human Judgment: A Bayesian Evaluation of LLMs’ Moral Values Understanding

August 20, 2025

Alina Landowska이 [arXiv]에 게시한 ‘Beyond Human Judgment: A Bayesian Evaluation of LLMs’ Moral Values Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Speed Always Wins: A Survey on Efficient Architectures for Large Language Models

August 19, 2025

Jusen Du이 [arXiv]에 게시한 ‘Speed Always Wins: A Survey on Efficient Architectures for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforcement Learning with Rubric Anchors

August 19, 2025

Haokai Xu이 [arXiv]에 게시한 ‘Reinforcement Learning with Rubric Anchors’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SSRL: Self-Search Reinforcement Learning

August 18, 2025

Yanxu Chen이 [arXiv]에 게시한 ‘SSRL: Self-Search Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models

August 15, 2025

Qinghao Ye이 [arXiv]에 게시한 ‘Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery

August 14, 2025

Di Zhang이 [arXiv]에 게시한 ‘Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models

August 14, 2025

Guiyang Hou이 [arXiv]에 게시한 ‘Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study

August 14, 2025

Gjergji Kasneci이 [arXiv]에 게시한 ‘Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance

August 14, 2025

Yong Li이 [arXiv]에 게시한 ‘AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Train Long, Think Short: Curriculum Learning for Efficient Reasoning

August 13, 2025

Marzyeh Ghassemi이 [arXiv]에 게시한 ‘Train Long, Think Short: Curriculum Learning for Efficient Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy

August 13, 2025

Elizabeth Karpinski이 [arXiv]에 게시한 ‘Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability

August 12, 2025

Yuchen Li이 [arXiv]에 게시한 ‘ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning

August 12, 2025

Jiaheng Liu이 [arXiv]에 게시한 ‘Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling

August 8, 2025

Ruolin Shen이 [arXiv]에 게시한 ‘Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling’ 논문에 대한 자세한 리뷰입...

[논문리뷰] R-Zero: Self-Evolving Reasoning LLM from Zero Data

August 8, 2025

Zongxia Li이 [arXiv]에 게시한 ‘R-Zero: Self-Evolving Reasoning LLM from Zero Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction

August 8, 2025

Prajit Das이 [arXiv]에 게시한 ‘PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking

August 8, 2025

Chao Wang이 [arXiv]에 게시한 ‘I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis

August 8, 2025

Reshmi Ghosh이 [arXiv]에 게시한 ‘Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Evaluating, Synthesizing, and Enhancing for Customer Support Conversation

August 8, 2025

Feng Chen이 [arXiv]에 게시한 ‘Evaluating, Synthesizing, and Enhancing for Customer Support Conversation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Are Today’s LLMs Ready to Explain Well-Being Concepts?

August 8, 2025

Huan Liu이 [arXiv]에 게시한 ‘Are Today’s LLMs Ready to Explain Well-Being Concepts?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning

August 7, 2025

Maksim Nekrashevich이 [arXiv]에 게시한 ‘Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Sotopia-RL: Reward Design for Social Intelligence

August 7, 2025

Keyang Xuan이 [arXiv]에 게시한 ‘Sotopia-RL: Reward Design for Social Intelligence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management

August 7, 2025

Yunxin Liu이 [arXiv]에 게시한 ‘Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks

August 7, 2025

Haozhe Zhang이 [arXiv]에 게시한 ‘Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization

August 7, 2025

Kechi Zhang이 [arXiv]에 게시한 ‘RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization’ 논문에 대한 자세한 리뷰입...

[논문리뷰] EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation

August 7, 2025

Dong Chen이 [arXiv]에 게시한 ‘EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Agent Lightning: Train ANY AI Agents with Reinforcement Learning

August 7, 2025

Zilong Wang이 [arXiv]에 게시한 ‘Agent Lightning: Train ANY AI Agents with Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search

August 6, 2025

Jiwei Li이 [arXiv]에 게시한 ‘CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models’ Instruction Following

August 5, 2025

Jiaqing Liang이 [arXiv]에 게시한 ‘Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models’ Instruction Following’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks

August 5, 2025

Zhiwei Zhang이 [arXiv]에 게시한 ‘AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution

August 4, 2025

Heng Lian이 [arXiv]에 게시한 ‘SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving

August 3, 2025

Zhicheng Jiang이 [arXiv]에 게시한 ‘Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Diffusion Models

[논문리뷰] CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching

September 24, 2025

Rui Qian이 [arXiv]에 게시한 ‘CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

September 23, 2025

Pengze Zhang이 [arXiv]에 게시한 ‘OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

September 23, 2025

Qinsheng Zhang이 [arXiv]에 게시한 ‘DiffusionNFT: Online Diffusion Reinforcement with Forward Process’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SPATIALGEN: Layout-guided 3D Indoor Scene Generation

September 22, 2025

Yongsen Mao이 [arXiv]에 게시한 ‘SPATIALGEN: Layout-guided 3D Indoor Scene Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue

September 22, 2025

Hui Zhang이 [arXiv]에 게시한 ‘Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Wan-Animate: Unified Character Animation and Replacement with Holistic Replication

September 18, 2025

Mingyang Huang이 [arXiv]에 게시한 ‘Wan-Animate: Unified Character Animation and Replacement with Holistic Replication’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation

September 17, 2025

Lixin Xu이 [arXiv]에 게시한 ‘Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Locality in Image Diffusion Models Emerges from Data Statistics

September 16, 2025

Vincent Sitzmann이 [arXiv]에 게시한 ‘Locality in Image Diffusion Models Emerges from Data Statistics’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence

September 16, 2025

Lionel M. Ni이 [arXiv]에 게시한 ‘LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] X-Part: high fidelity and structure coherent shape decomposition

September 15, 2025

Yunhan Yang이 [arXiv]에 게시한 ‘X-Part: high fidelity and structure coherent shape decomposition’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis

September 15, 2025

Song Guo이 [arXiv]에 게시한 ‘InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies

September 15, 2025

Fabian Otto이 [arXiv]에 게시한 ‘FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

September 12, 2025

Zhuowei Chen이 [arXiv]에 게시한 ‘HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward

September 10, 2025

Fei Ding이 [arXiv]에 게시한 ‘UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling

September 10, 2025

Diana Marculescu이 [arXiv]에 게시한 ‘Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

September 10, 2025

Yingfang Zhang이 [arXiv]에 게시한 ‘Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Interleaving Reasoning for Better Text-to-Image Generation

September 9, 2025

Shixiang Tang이 [arXiv]에 게시한 ‘Interleaving Reasoning for Better Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Set Block Decoding is a Language Model Inference Accelerator

September 8, 2025

Jeremy Reizenstein이 [arXiv]에 게시한 ‘Set Block Decoding is a Language Model Inference Accelerator’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LuxDiT: Lighting Estimation with Video Diffusion Transformer

September 8, 2025

Sanja Fidler이 [arXiv]에 게시한 ‘LuxDiT: Lighting Estimation with Video Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Transition Models: Rethinking the Generative Learning Objective

September 5, 2025

Yangguang Li이 [arXiv]에 게시한 ‘Transition Models: Rethinking the Generative Learning Objective’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Durian: Dual Reference-guided Portrait Animation with Attribute Transfer

September 5, 2025

Hanbyul Joo이 [arXiv]에 게시한 ‘Durian: Dual Reference-guided Portrait Animation with Attribute Transfer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement

September 4, 2025

Hualiang Wang이 [arXiv]에 게시한 ‘MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GenCompositor: Generative Video Compositing with Diffusion Transformer

September 3, 2025

Lingen Li이 [arXiv]에 게시한 ‘GenCompositor: Generative Video Compositing with Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models

September 3, 2025

Zhen Wang이 [arXiv]에 게시한 ‘FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning

August 29, 2025

Jiahe Tian이 [arXiv]에 게시한 ‘USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Collaborative Multi-Modal Coding for High-Quality 3D Generation

August 29, 2025

Ziwei Liu이 [arXiv]에 게시한 ‘Collaborative Multi-Modal Coding for High-Quality 3D Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation

August 28, 2025

Yan Zhou이 [arXiv]에 게시한 ‘MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AudioStory: Generating Long-Form Narrative Audio with Large Language Models

August 28, 2025

Yixiao Ge이 [arXiv]에 게시한 ‘AudioStory: Generating Long-Form Narrative Audio with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Wan-S2V: Audio-Driven Cinematic Video Generation

August 27, 2025

Chaonan Ji이 [arXiv]에 게시한 ‘Wan-S2V: Audio-Driven Cinematic Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space

August 27, 2025

Rui Chen이 [arXiv]에 게시한 ‘VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CineScale: Free Lunch in High-Resolution Cinematic Visual Generation

August 27, 2025

Ziwei Liu이 [arXiv]에 게시한 ‘CineScale: Free Lunch in High-Resolution Cinematic Visual Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SpotEdit: Evaluating Visually-Guided Image Editing Methods

August 26, 2025

Ersin Yumer이 [arXiv]에 게시한 ‘SpotEdit: Evaluating Visually-Guided Image Editing Methods’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MV-RAG: Retrieval Augmented Multiview Diffusion

August 26, 2025

sagiebenaim이 [arXiv]에 게시한 ‘MV-RAG: Retrieval Augmented Multiview Diffusion’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass

August 22, 2025

Ya Zhang이 [arXiv]에 게시한 ‘SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Tinker: Diffusion’s Gift to 3D–Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization

August 21, 2025

Hao Chen이 [arXiv]에 게시한 ‘Tinker: Diffusion’s Gift to 3D–Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models

August 19, 2025

Meiqi Wu이 [arXiv]에 게시한 ‘S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Precise Action-to-Video Generation Through Visual Action Prompts

August 19, 2025

Minghan Qin이 [arXiv]에 게시한 ‘Precise Action-to-Video Generation Through Visual Action Prompts’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model

August 19, 2025

Yifan Zhang이 [arXiv]에 게시한 ‘Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models

August 19, 2025

Zixiang Gao이 [arXiv]에 게시한 ‘Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 4DNeX: Feed-Forward 4D Generative Modeling Made Easy

August 19, 2025

Zeng Tao이 [arXiv]에 게시한 ‘4DNeX: Feed-Forward 4D Generative Modeling Made Easy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

August 18, 2025

Mu Xu이 [arXiv]에 게시한 ‘FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Story2Board: A Training-Free Approach for Expressive Storyboard Generation

August 14, 2025

Dani Lischinski이 [arXiv]에 게시한 ‘Story2Board: A Training-Free Approach for Expressive Storyboard Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation

August 14, 2025

Chen Li이 [arXiv]에 게시한 ‘Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models

August 14, 2025

Zeynep Akata이 [arXiv]에 게시한 ‘Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Matrix-3D: Omnidirectional Explorable 3D World Generation

August 13, 2025

Yuqi Li이 [arXiv]에 게시한 ‘Matrix-3D: Omnidirectional Explorable 3D World Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CharacterShot: Controllable and Consistent 4D Character Animation

August 13, 2025

Fei Shen이 [arXiv]에 게시한 ‘CharacterShot: Controllable and Consistent 4D Character Animation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation

August 12, 2025

Xiaokun Feng이 [arXiv]에 게시한 ‘Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control

August 12, 2025

Hongyu Liu이 [arXiv]에 게시한 ‘Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LightSwitch: Multi-view Relighting with Material-guided Diffusion

August 11, 2025

Shubham Tulsiani이 [arXiv]에 게시한 ‘LightSwitch: Multi-view Relighting with Material-guided Diffusion’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] StrandDesigner: Towards Practical Strand Generation with Sketch Guidance

August 8, 2025

Xiaobin Hu이 [arXiv]에 게시한 ‘StrandDesigner: Towards Practical Strand Generation with Sketch Guidance’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression

August 8, 2025

Yifei Ji이 [arXiv]에 게시한 ‘Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models

August 7, 2025

Elisabetta Rocchetti이 [arXiv]에 게시한 ‘The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

August 7, 2025

Feng Zhao이 [arXiv]에 게시한 ‘Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

August 6, 2025

Fan Xia이 [arXiv]에 게시한 ‘Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Multi-human Interactive Talking Dataset

August 6, 2025

Mike Zheng Shou이 [arXiv]에 게시한 ‘Multi-human Interactive Talking Dataset’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation

August 6, 2025

Chenyang Si이 [arXiv]에 게시한 ‘LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer

August 6, 2025

Shunyu Yao이 [arXiv]에 게시한 ‘LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation

August 4, 2025

Long Chen이 [arXiv]에 게시한 ‘SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PixNerd: Pixel Neural Field Diffusion

August 4, 2025

Limin Wang이 [arXiv]에 게시한 ‘PixNerd: Pixel Neural Field Diffusion’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models

August 3, 2025

Kaixin Wang이 [arXiv]에 게시한 ‘villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Benchmark

[논문리뷰] VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction

September 24, 2025

So Fukuda이 [arXiv]에 게시한 ‘VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OpenGVL - Benchmarking Visual Temporal Progress for Data Curation

September 24, 2025

Viktor Petrenko이 [arXiv]에 게시한 ‘OpenGVL - Benchmarking Visual Temporal Progress for Data Curation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR

September 24, 2025

Zeina Aldallal이 [arXiv]에 게시한 ‘Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery

September 23, 2025

Shiya Huang이 [arXiv]에 게시한 ‘VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

September 23, 2025

Yannis Yiming He이 [arXiv]에 게시한 ‘SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects

September 23, 2025

Hang Yu이 [arXiv]에 게시한 ‘CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?

September 23, 2025

Jaeho Lee이 [arXiv]에 게시한 ‘AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ARE: Scaling Up Agent Environments and Evaluations

September 23, 2025

Matteo Bettini이 [arXiv]에 게시한 ‘ARE: Scaling Up Agent Environments and Evaluations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

September 18, 2025

Zhun Wang이 [arXiv]에 게시한 ‘SteeringControl: Holistic Evaluation of Alignment Steering in LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GenExam: A Multidisciplinary Text-to-Image Exam

September 18, 2025

Yu Qiao이 [arXiv]에 게시한 ‘GenExam: A Multidisciplinary Text-to-Image Exam’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Measuring Epistemic Humility in Multimodal Large Language Models

September 16, 2025

Kaiyang Zhou이 [arXiv]에 게시한 ‘Measuring Epistemic Humility in Multimodal Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions

September 15, 2025

Dong Zhang이 [arXiv]에 게시한 ‘VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China

September 15, 2025

XU Han이 [arXiv]에 게시한 ‘CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering

September 12, 2025

Jianguo Zhang이 [arXiv]에 게시한 ‘LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark

September 12, 2025

Shuai Bai이 [arXiv]에 게시한 ‘FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants

September 11, 2025

Jacy Reese Anthis이 [arXiv]에 게시한 ‘HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge

September 10, 2025

Dipanjan Das이 [arXiv]에 게시한 ‘SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents

September 9, 2025

Zhengxi Lu이 [arXiv]에 게시한 ‘MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?

September 5, 2025

Yu Fu이 [arXiv]에 게시한 ‘Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks

September 5, 2025

Jiaxuan Lu이 [arXiv]에 게시한 ‘DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games

September 3, 2025

Dongmin Park이 [arXiv]에 게시한 ‘FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding

September 3, 2025

Xuanyu Zheng이 [arXiv]에 게시한 ‘ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks

August 27, 2025

Kai Jia이 [arXiv]에 게시한 ‘ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics

August 27, 2025

Dongchen Huang이 [arXiv]에 게시한 ‘CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SpotEdit: Evaluating Visually-Guided Image Editing Methods

August 26, 2025

Ersin Yumer이 [arXiv]에 게시한 ‘SpotEdit: Evaluating Visually-Guided Image Editing Methods’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions

August 25, 2025

Yidi Du이 [arXiv]에 게시한 ‘AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] INTIMA: A Benchmark for Human-AI Companionship Behavior

August 22, 2025

Yacine Jernite이 [arXiv]에 게시한 ‘INTIMA: A Benchmark for Human-AI Companionship Behavior’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MultiRef: Controllable Image Generation with Multiple Visual References

August 20, 2025

Shiyun Lang이 [arXiv]에 게시한 ‘MultiRef: Controllable Image Generation with Multiple Visual References’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence

August 20, 2025

Fernando López이 [arXiv]에 게시한 ‘MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents

August 20, 2025

Jun Dong이 [arXiv]에 게시한 ‘MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds

August 19, 2025

Artyom Sorokin이 [arXiv]에 게시한 ‘HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models

August 14, 2025

Dongdong Zhang이 [arXiv]에 게시한 ‘VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WideSearch: Benchmarking Agentic Broad Info-Seeking

August 12, 2025

Yan Gao이 [arXiv]에 게시한 ‘WideSearch: Benchmarking Agentic Broad Info-Seeking’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

August 12, 2025

Tong Yu이 [arXiv]에 게시한 ‘VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes

August 8, 2025

Xudong Jiang이 [arXiv]에 게시한 ‘MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning

August 8, 2025

Ziming Wang이 [arXiv]에 게시한 ‘DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?

August 6, 2025

Yaojie Lu이 [arXiv]에 게시한 ‘LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLMs

[논문리뷰] SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

September 23, 2025

Yannis Yiming He이 [arXiv]에 게시한 ‘SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token’s Nature

September 23, 2025

Bin Cui이 [arXiv]에 게시한 ‘From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token’s Nature’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EpiCache: Episodic KV Cache Management for Long Conversational Question Answering

September 23, 2025

Minsik Cho이 [arXiv]에 게시한 ‘EpiCache: Episodic KV Cache Management for Long Conversational Question Answering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects

September 23, 2025

Hang Yu이 [arXiv]에 게시한 ‘CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation

September 22, 2025

Steven Liu이 [arXiv]에 게시한 ‘RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration

September 19, 2025

Zhilin Wang이 [arXiv]에 게시한 ‘Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation

September 19, 2025

Kishan Panaganti이 [arXiv]에 게시한 ‘Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning

September 17, 2025

Huifeng Yin이 [arXiv]에 게시한 ‘WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings

September 16, 2025

Yixuan Tang이 [arXiv]에 게시한 ‘GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] So let's replace this phrase with insult... Lessons learned from generation of toxic texts with LLMs

September 11, 2025

Alexander Panchenko이 [arXiv]에 게시한 ‘ So let's replace this phrase with insult... Lessons learned from generation of toxic texts with LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Survey of Reinforcement Learning for Large Reasoning Models

September 11, 2025

Runze Liu이 [arXiv]에 게시한 ‘A Survey of Reinforcement Learning for Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ΔL Normalization: Rethink Loss Aggregation in RLVR

September 10, 2025

Lili Qiu이 [arXiv]에 게시한 ‘ΔL Normalization: Rethink Loss Aggregation in RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reverse-Engineered Reasoning for Open-Ended Generation

September 9, 2025

Wangchunshu Zhou이 [arXiv]에 게시한 ‘Reverse-Engineered Reasoning for Open-Ended Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?

September 5, 2025

Yu Fu이 [arXiv]에 게시한 ‘Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang

September 3, 2025

Solomon Tsai이 [arXiv]에 게시한 ‘The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic

September 3, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Metis: Training Large Language Models with Advanced Low-Bit Quantization

September 3, 2025

Hengjie Cao이 [arXiv]에 게시한 ‘Metis: Training Large Language Models with Advanced Low-Bit Quantization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games

September 3, 2025

Dongmin Park이 [arXiv]에 게시한 ‘FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning

August 27, 2025

Ran Guo이 [arXiv]에 게시한 ‘UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models

August 27, 2025

Jiangjie Chen이 [arXiv]에 게시한 ‘ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ST-Raptor: LLM-Powered Semi-Structured Table Question Answering

August 26, 2025

Wei Zhou이 [arXiv]에 게시한 ‘ST-Raptor: LLM-Powered Semi-Structured Table Question Answering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CRISP: Persistent Concept Unlearning via Sparse Autoencoders

August 25, 2025

Yonatan Belinkov이 [arXiv]에 게시한 ‘CRISP: Persistent Concept Unlearning via Sparse Autoencoders’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists

August 22, 2025

Heng Zhang이 [arXiv]에 게시한 ‘aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation

August 20, 2025

Xinyi Wang이 [arXiv]에 게시한 ‘Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

August 20, 2025

Liam-Liu이 [arXiv]에 게시한 ‘Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] BiasGym: Fantastic Biases and How to Find (and Remove) Them

August 13, 2025

Arnav Arora이 [arXiv]에 게시한 ‘BiasGym: Fantastic Biases and How to Find (and Remove) Them’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning

August 12, 2025

Baihong Yuan이 [arXiv]에 게시한 ‘Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts

August 12, 2025

Tieyuan Chen이 [arXiv]에 게시한 ‘Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs

August 12, 2025

Robert Kirk이 [arXiv]에 게시한 ‘Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

August 12, 2025

Kai Zou이 [arXiv]에 게시한 ‘BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal

August 11, 2025

Chengcheng Wan이 [arXiv]에 게시한 ‘Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh

August 11, 2025

Yi Yang이 [arXiv]에 게시한 ‘MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following

August 7, 2025

Liang Xu이 [arXiv]에 게시한 ‘Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens

August 7, 2025

Zhen Tan이 [arXiv]에 게시한 ‘Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards

August 7, 2025

Ling-I Wu이 [arXiv]에 게시한 ‘IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vision-Language Models

[논문리뷰] MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction

September 23, 2025

Xintao Chen이 [arXiv]에 게시한 ‘MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue

September 22, 2025

Hui Zhang이 [arXiv]에 게시한 ‘Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

September 19, 2025

Zehao Li이 [arXiv]에 게시한 ‘ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence

September 19, 2025

Qinghua Huang이 [arXiv]에 게시한 ‘EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 3D Aware Region Prompted Vision Language Model

September 17, 2025

Xiaolong Li이 [arXiv]에 게시한 ‘3D Aware Region Prompted Vision Language Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Lost in Embeddings: Information Loss in Vision-Language Models

September 16, 2025

Ivan Vulić이 [arXiv]에 게시한 ‘Lost in Embeddings: Information Loss in Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models

September 16, 2025

Shuo Ren이 [arXiv]에 게시한 ‘Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual Representation Alignment for Multimodal Large Language Models

September 10, 2025

Heeseong Shin이 [arXiv]에 게시한 ‘Visual Representation Alignment for Multimodal Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MobiAgent: A Systematic Framework for Customizable Mobile Agents

September 3, 2025

Wangbo Gong이 [arXiv]에 게시한 ‘MobiAgent: A Systematic Framework for Customizable Mobile Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mimicking the Physicist’s Eye:A VLM-centric Approach for Physics Formula Discovery

September 1, 2025

Wenjie Zhou이 [arXiv]에 게시한 ‘Mimicking the Physicist’s Eye:A VLM-centric Approach for Physics Formula Discovery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CLIPSym: Delving into Symmetry Detection with CLIP

September 1, 2025

Raymond A. Yeh이 [arXiv]에 게시한 ‘CLIPSym: Delving into Symmetry Detection with CLIP’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning

August 29, 2025

Yitong Wang이 [arXiv]에 게시한 ‘OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Self-Rewarding Vision-Language Model via Reasoning Decomposition

August 28, 2025

Zhenwen Liang이 [arXiv]에 게시한 ‘Self-Rewarding Vision-Language Model via Reasoning Decomposition’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment

August 26, 2025

Doratossadat Dastgheib이 [arXiv]에 게시한 ‘MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

August 26, 2025

jinglinglin이 [arXiv]에 게시한 ‘InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Explain Before You Answer: A Survey on Compositional Visual Reasoning

August 26, 2025

Xin Zheng이 [arXiv]에 게시한 ‘Explain Before You Answer: A Survey on Compositional Visual Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents

August 20, 2025

Jun Dong이 [arXiv]에 게시한 ‘MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping

August 19, 2025

Tyler Derr이 [arXiv]에 게시한 ‘Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors

August 13, 2025

Haoran Xu이 [arXiv]에 게시한 ‘Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Test-Time Reinforcement Learning for GUI Grounding via Region Consistency

August 13, 2025

Zhengxi Lu이 [arXiv]에 게시한 ‘Test-Time Reinforcement Learning for GUI Grounding via Region Consistency’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OpenCUA: Open Foundations for Computer-Use Agents

August 13, 2025

Tianbao Xie이 [arXiv]에 게시한 ‘OpenCUA: Open Foundations for Computer-Use Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MolmoAct: Action Reasoning Models that can Reason in Space

August 12, 2025

Shuo Liu이 [arXiv]에 게시한 ‘MolmoAct: Action Reasoning Models that can Reason in Space’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience

August 7, 2025

Xiaoyi Dong이 [arXiv]에 게시한 ‘SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success

August 7, 2025

Ruslan Rakhimov이 [arXiv]에 게시한 ‘Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success’ 논문에 대한 자세한 리뷰...

[논문리뷰] DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework

August 7, 2025

Chao Liang이 [arXiv]에 게시한 ‘DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Multimodal Referring Segmentation: A Survey

August 4, 2025

Zuxuan Wu이 [arXiv]에 게시한 ‘Multimodal Referring Segmentation: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AgroBench: Vision-Language Model Benchmark in Agriculture

August 3, 2025

Yoshitaka Ushiku이 [arXiv]에 게시한 ‘AgroBench: Vision-Language Model Benchmark in Agriculture’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Chain-of-Thought

[논문리뷰] What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT

September 24, 2025

Anthony Hartshorn이 [arXiv]에 게시한 ‘What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

September 23, 2025

Shaohui Jiao이 [arXiv]에 게시한 ‘TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?

September 23, 2025

Jaeho Lee이 [arXiv]에 게시한 ‘AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving

September 17, 2025

Shansan Gong이 [arXiv]에 게시한 ‘EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated

September 12, 2025

Jamie Hayes이 [arXiv]에 게시한 ‘Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet

September 9, 2025

See-Kiong Ng이 [arXiv]에 게시한 ‘Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction

September 3, 2025

bindsch이 [arXiv]에 게시한 ‘SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic

September 3, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Kwai Keye-VL 1.5 Technical Report

September 3, 2025

SXxtyz이 [arXiv]에 게시한 ‘Kwai Keye-VL 1.5 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] StepWiser: Stepwise Generative Judges for Wiser Reasoning

August 28, 2025

Olga Golovneva이 [arXiv]에 게시한 ‘StepWiser: Stepwise Generative Judges for Wiser Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning

August 27, 2025

Arman Cohan이 [arXiv]에 게시한 ‘Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Explain Before You Answer: A Survey on Compositional Visual Reasoning

August 26, 2025

Xin Zheng이 [arXiv]에 게시한 ‘Explain Before You Answer: A Survey on Compositional Visual Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling

August 26, 2025

Daniil Orel이 [arXiv]에 게시한 ‘Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery

August 14, 2025

Di Zhang이 [arXiv]에 게시한 ‘Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Train Long, Think Short: Curriculum Learning for Efficient Reasoning

August 13, 2025

Marzyeh Ghassemi이 [arXiv]에 게시한 ‘Train Long, Think Short: Curriculum Learning for Efficient Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Aryabhata: An exam-focused language model for JEE Math

August 13, 2025

Sandeep Varma이 [arXiv]에 게시한 ‘Aryabhata: An exam-focused language model for JEE Math’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Compressing Chain-of-Thought in LLMs via Step Entropy

August 12, 2025

Zhijian Xu이 [arXiv]에 게시한 ‘Compressing Chain-of-Thought in LLMs via Step Entropy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Don’t Overthink It: A Survey of Efficient R1-style Large Reasoning Models

August 8, 2025

Fangzhou Yao이 [arXiv]에 게시한 ‘Don’t Overthink It: A Survey of Efficient R1-style Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks

August 7, 2025

Haozhe Zhang이 [arXiv]에 게시한 ‘Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens

August 7, 2025

Zhen Tan이 [arXiv]에 게시한 ‘Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HPSv3: Towards Wide-Spectrum Human Preference Score

August 7, 2025

Hongsheng Li이 [arXiv]에 게시한 ‘HPSv3: Towards Wide-Spectrum Human Preference Score’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction

August 7, 2025

Donghyeon Lee이 [arXiv]에 게시한 ‘CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

August 4, 2025

Hao Tang이 [arXiv]에 게시한 ‘3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving

August 3, 2025

Zhicheng Jiang이 [arXiv]에 게시한 ‘Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Large Language Models (LLMs)

[논문리뷰] Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels

September 23, 2025

Qi Zhang이 [arXiv]에 게시한 ‘Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents

September 22, 2025

Chao Zhang이 [arXiv]에 게시한 ‘Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook

September 18, 2025

Bowen Zhou이 [arXiv]에 게시한 ‘MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Improving Context Fidelity via Native Retrieval-Augmented Reasoning

September 18, 2025

Xiangru Tang이 [arXiv]에 게시한 ‘Improving Context Fidelity via Native Retrieval-Augmented Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward

September 12, 2025

Xiaoyu Tan이 [arXiv]에 게시한 ‘The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward’ 논문에 대한...

[논문리뷰] WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents

September 9, 2025

Aili Chen이 [arXiv]에 게시한 ‘WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Bootstrapping Task Spaces for Self-Improvement

September 8, 2025

Yoram Bachrach이 [arXiv]에 게시한 ‘Bootstrapping Task Spaces for Self-Improvement’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Towards a Unified View of Large Language Model Post-Training

September 5, 2025

Hongyi Liu이 [arXiv]에 게시한 ‘Towards a Unified View of Large Language Model Post-Training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings

September 5, 2025

Oren Glickman이 [arXiv]에 게시한 ‘NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation

September 3, 2025

Xiaolei Huang이 [arXiv]에 게시한 ‘Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation’ 논문에 대한 자...

[논문리뷰] T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables

September 2, 2025

Yu Zhao이 [arXiv]에 게시한 ‘T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning

September 2, 2025

Yuewei Zhang이 [arXiv]에 게시한 ‘PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD

August 29, 2025

Roy Ka-Wei Lee이 [arXiv]에 게시한 ‘Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models

August 29, 2025

Alex Endert이 [arXiv]에 게시한 ‘OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Spacer: Towards Engineered Scientific Inspiration

August 27, 2025

zerojun48이 [arXiv]에 게시한 ‘Spacer: Towards Engineered Scientific Inspiration’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries

August 22, 2025

huuuyeah이 [arXiv]에 게시한 ‘LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Leveraging Large Language Models for Predictive Analysis of Human Misery

August 20, 2025

Abhilash Nandy이 [arXiv]에 게시한 ‘Leveraging Large Language Models for Predictive Analysis of Human Misery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation

August 13, 2025

Rachel Bawden이 [arXiv]에 게시한 ‘TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay

August 13, 2025

Yang Fan이 [arXiv]에 게시한 ‘GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments

August 13, 2025

Xuesong Yao이 [arXiv]에 게시한 ‘Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Tool-integrated Reinforcement Learning for Repo Deep Search

August 6, 2025

Yanzhen Zou이 [arXiv]에 게시한 ‘Tool-integrated Reinforcement Learning for Repo Deep Search’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RecGPT Technical Report

August 3, 2025

Jian Wu이 [arXiv]에 게시한 ‘RecGPT Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Persona Vectors: Monitoring and Controlling Character Traits in Language Models

August 3, 2025

Jack Lindsey이 [arXiv]에 게시한 ‘Persona Vectors: Monitoring and Controlling Character Traits in Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal AI

[논문리뷰] Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation

September 24, 2025

Jianbin Zheng이 [arXiv]에 게시한 ‘Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions

September 23, 2025

tengdai722이 [arXiv]에 게시한 ‘FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questio...

[논문리뷰] Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents

September 22, 2025

Chao Zhang이 [arXiv]에 게시한 ‘Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence

September 19, 2025

Qinghua Huang이 [arXiv]에 게시한 ‘EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AToken: A Unified Tokenizer for Vision

September 19, 2025

Mingze Xu이 [arXiv]에 게시한 ‘AToken: A Unified Tokenizer for Vision’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits

September 16, 2025

Zhenhao Chen이 [arXiv]에 게시한 ‘PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Lost in Embeddings: Information Loss in Vision-Language Models

September 16, 2025

Ivan Vulić이 [arXiv]에 게시한 ‘Lost in Embeddings: Information Loss in Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding

September 16, 2025

Li Zheng이 [arXiv]에 게시한 ‘Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Groundi...

[논문리뷰] Visual Programmability: A Guide for Code-as-Thought in Chart Understanding

September 12, 2025

Ethan Chern이 [arXiv]에 게시한 ‘Visual Programmability: A Guide for Code-as-Thought in Chart Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Survey of Reinforcement Learning for Large Reasoning Models

September 11, 2025

Runze Liu이 [arXiv]에 게시한 ‘A Survey of Reinforcement Learning for Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforcement Learning Foundations for Deep Research Systems: A Survey

September 9, 2025

Wei Han이 [arXiv]에 게시한 ‘Reinforcement Learning Foundations for Deep Research Systems: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mimicking the Physicist’s Eye:A VLM-centric Approach for Physics Formula Discovery

September 1, 2025

Wenjie Zhou이 [arXiv]에 게시한 ‘Mimicking the Physicist’s Eye:A VLM-centric Approach for Physics Formula Discovery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification

August 29, 2025

Liqiang Nie이 [arXiv]에 게시한 ‘CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AudioStory: Generating Long-Form Narrative Audio with Large Language Models

August 28, 2025

Yixiao Ge이 [arXiv]에 게시한 ‘AudioStory: Generating Long-Form Narrative Audio with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Explain Before You Answer: A Survey on Compositional Visual Reasoning

August 26, 2025

Xin Zheng이 [arXiv]에 게시한 ‘Explain Before You Answer: A Survey on Compositional Visual Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding

August 22, 2025

Rui Guo이 [arXiv]에 게시한 ‘When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?

August 21, 2025

Daeyoung Kim이 [arXiv]에 게시한 ‘ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence

August 20, 2025

Fernando López이 [arXiv]에 게시한 ‘MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Survey on Diffusion Language Models

August 15, 2025

Zhiqiang Shen이 [arXiv]에 게시한 ‘A Survey on Diffusion Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences

August 12, 2025

Matvey Skripkin이 [arXiv]에 게시한 ‘Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh

August 11, 2025

Yi Yang이 [arXiv]에 게시한 ‘MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation

August 6, 2025

Tianyidan Xie이 [arXiv]에 게시한 ‘Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Tool Use

[논문리뷰] ARE: Scaling Up Agent Environments and Evaluations

September 23, 2025

Matteo Bettini이 [arXiv]에 게시한 ‘ARE: Scaling Up Agent Environments and Evaluations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning

September 19, 2025

Jiashuo Liu이 [arXiv]에 게시한 ‘FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Towards General Agentic Intelligence via Environment Scaling

September 17, 2025

Guangyu Li이 [arXiv]에 게시한 ‘Towards General Agentic Intelligence via Environment Scaling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Scaling Agents via Continual Pre-training

September 17, 2025

Guangyu Li이 [arXiv]에 게시한 ‘Scaling Agents via Continual Pre-training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools

September 15, 2025

Xiaorui Wang이 [arXiv]에 게시한 ‘MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforcement Learning Foundations for Deep Research Systems: A Survey

September 9, 2025

Wei Han이 [arXiv]에 게시한 ‘Reinforcement Learning Foundations for Deep Research Systems: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use

September 3, 2025

Zhiheng Lyu이 [arXiv]에 게시한 ‘VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

September 3, 2025

Hejia Geng이 [arXiv]에 게시한 ‘The Landscape of Agentic Reinforcement Learning for LLMs: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench

September 2, 2025

Jayanth Srinivasa이 [arXiv]에 게시한 ‘How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench’ 논문에 대한 자세한 리뷰입...

[논문리뷰] rStar2-Agent: Agentic Reasoning Technical Report

August 29, 2025

Weijiang Xu이 [arXiv]에 게시한 ‘rStar2-Agent: Agentic Reasoning Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

August 29, 2025

Shashank Biju이 [arXiv]에 게시한 ‘MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications

August 25, 2025

Liuyi Yao이 [arXiv]에 게시한 ‘AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries

August 22, 2025

huuuyeah이 [arXiv]에 게시한 ‘LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers

August 21, 2025

Prathyusha Jwalapuram이 [arXiv]에 게시한 ‘MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

August 21, 2025

tianlecai이 [arXiv]에 게시한 ‘FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents

August 20, 2025

Jun Dong이 [arXiv]에 게시한 ‘MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving

August 14, 2025

Jinjie Gu이 [arXiv]에 게시한 ‘AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments

August 13, 2025

Xuesong Yao이 [arXiv]에 게시한 ‘Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL

August 13, 2025

Chuyi He이 [arXiv]에 게시한 ‘Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UserBench: An Interactive Gym Environment for User-Centric Agents

August 12, 2025

Jianguo Zhang이 [arXiv]에 게시한 ‘UserBench: An Interactive Gym Environment for User-Centric Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks

August 12, 2025

Hongxing Li이 [arXiv]에 게시한 ‘OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

August 12, 2025

Xinhao Yi이 [arXiv]에 게시한 ‘A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems’ 논문에 대한 자세...

Back to Top ↑

Generative Models

[논문리뷰] VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models

September 23, 2025

Sunghyun Cho이 [arXiv]에 게시한 ‘VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AToken: A Unified Tokenizer for Vision

September 19, 2025

Mingze Xu이 [arXiv]에 게시한 ‘AToken: A Unified Tokenizer for Vision’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Locality in Image Diffusion Models Emerges from Data Statistics

September 16, 2025

Vincent Sitzmann이 [arXiv]에 게시한 ‘Locality in Image Diffusion Models Emerges from Data Statistics’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 2D Gaussian Splatting with Semantic Alignment for Image Inpainting

September 12, 2025

Guangming Lu이 [arXiv]에 게시한 ‘2D Gaussian Splatting with Semantic Alignment for Image Inpainting’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 3D and 4D World Modeling: A Survey

September 11, 2025

Ao Liang이 [arXiv]에 게시한 ‘3D and 4D World Modeling: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LuxDiT: Lighting Estimation with Video Diffusion Transformer

September 8, 2025

Sanja Fidler이 [arXiv]에 게시한 ‘LuxDiT: Lighting Estimation with Video Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Transition Models: Rethinking the Generative Learning Objective

September 5, 2025

Yangguang Li이 [arXiv]에 게시한 ‘Transition Models: Rethinking the Generative Learning Objective’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views

September 3, 2025

Junchi Yan이 [arXiv]에 게시한 ‘Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Vie...

[논문리뷰] LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

September 3, 2025

Jianwei Yang이 [arXiv]에 게시한 ‘LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GenCompositor: Generative Video Compositing with Diffusion Transformer

September 3, 2025

Lingen Li이 [arXiv]에 게시한 ‘GenCompositor: Generative Video Compositing with Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mixture of Contexts for Long Video Generation

August 29, 2025

Junfei Xiao이 [arXiv]에 게시한 ‘Mixture of Contexts for Long Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FakeParts: a New Family of AI-Generated DeepFakes

August 29, 2025

Xi Wang이 [arXiv]에 게시한 ‘FakeParts: a New Family of AI-Generated DeepFakes’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models

August 27, 2025

Beiqi Chen이 [arXiv]에 게시한 ‘ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Selective Contrastive Learning for Weakly Supervised Affordance Grounding

August 25, 2025

Jae-Pil Heo이 [arXiv]에 게시한 ‘Selective Contrastive Learning for Weakly Supervised Affordance Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Semantic IDs for Joint Generative Search and Recommendation

August 20, 2025

Enrico Palumbo이 [arXiv]에 게시한 ‘Semantic IDs for Joint Generative Search and Recommendation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models

August 19, 2025

Meiqi Wu이 [arXiv]에 게시한 ‘S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models

August 19, 2025

Zixiang Gao이 [arXiv]에 게시한 ‘Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 4DNeX: Feed-Forward 4D Generative Modeling Made Easy

August 19, 2025

Zeng Tao이 [arXiv]에 게시한 ‘4DNeX: Feed-Forward 4D Generative Modeling Made Easy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control

August 12, 2025

Hongyu Liu이 [arXiv]에 게시한 ‘Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering

August 7, 2025

Ambuj Mehrish이 [arXiv]에 게시한 ‘SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PixNerd: Pixel Neural Field Diffusion

August 4, 2025

Limin Wang이 [arXiv]에 게시한 ‘PixNerd: Pixel Neural Field Diffusion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Evaluation

[논문리뷰] FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions

September 23, 2025

tengdai722이 [arXiv]에 게시한 ‘FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questio...

[논문리뷰] DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultural Text Adaptation in Indian Context

September 23, 2025

Maunendra Sankar Desarkar이 [arXiv]에 게시한 ‘DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultur...

[논문리뷰] Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs

September 19, 2025

Katharina von der Wense이 [arXiv]에 게시한 ‘Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools

September 15, 2025

Xiaorui Wang이 [arXiv]에 게시한 ‘MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants

September 11, 2025

Jacy Reese Anthis이 [arXiv]에 게시한 ‘HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On Robustness and Reliability of Benchmark-Based Evaluation of LLMs

September 8, 2025

Kevin Roitero이 [arXiv]에 게시한 ‘On Robustness and Reliability of Benchmark-Based Evaluation of LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks

September 5, 2025

Jiaxuan Lu이 [arXiv]에 게시한 ‘DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code

September 1, 2025

Libo Chen이 [arXiv]에 게시한 ‘A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks

August 27, 2025

Kai Jia이 [arXiv]에 게시한 ‘ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UQ: Assessing Language Models on Unsolved Questions

August 26, 2025

Wei Liu이 [arXiv]에 게시한 ‘UQ: Assessing Language Models on Unsolved Questions’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles

August 25, 2025

Diping Song이 [arXiv]에 게시한 ‘InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions

August 25, 2025

Yidi Du이 [arXiv]에 게시한 ‘AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning

August 21, 2025

anoperson이 [arXiv]에 게시한 ‘mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models

August 21, 2025

Ziyan Kuang이 [arXiv]에 게시한 ‘From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds

August 19, 2025

Artyom Sorokin이 [arXiv]에 게시한 ‘HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy

August 13, 2025

Elizabeth Karpinski이 [arXiv]에 게시한 ‘Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UserBench: An Interactive Gym Environment for User-Centric Agents

August 12, 2025

Jianguo Zhang이 [arXiv]에 게시한 ‘UserBench: An Interactive Gym Environment for User-Centric Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Are Today’s LLMs Ready to Explain Well-Being Concepts?

August 8, 2025

Huan Liu이 [arXiv]에 게시한 ‘Are Today’s LLMs Ready to Explain Well-Being Concepts?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward

August 6, 2025

Songyang Gao이 [arXiv]에 게시한 ‘CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations

August 3, 2025

Yiwen Guo이 [arXiv]에 게시한 ‘C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agentic AI

[논문리뷰] WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning

September 17, 2025

Huifeng Yin이 [arXiv]에 게시한 ‘WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents

September 17, 2025

Wenbiao Yin이 [arXiv]에 게시한 ‘WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Towards General Agentic Intelligence via Environment Scaling

September 17, 2025

Guangyu Li이 [arXiv]에 게시한 ‘Towards General Agentic Intelligence via Environment Scaling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs

September 15, 2025

Jonas Geiping이 [arXiv]에 게시한 ‘The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools

September 15, 2025

Xiaorui Wang이 [arXiv]에 게시한 ‘MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EnvX: Agentize Everything with Agentic AI

September 11, 2025

Wenzheng Tom Tang이 [arXiv]에 게시한 ‘EnvX: Agentize Everything with Agentic AI’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Survey of Reinforcement Learning for Large Reasoning Models

September 11, 2025

Runze Liu이 [arXiv]에 게시한 ‘A Survey of Reinforcement Learning for Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforcement Learning Foundations for Deep Research Systems: A Survey

September 9, 2025

Wei Han이 [arXiv]에 게시한 ‘Reinforcement Learning Foundations for Deep Research Systems: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Open Data Synthesis For Deep Research

September 4, 2025

Zheng Liu이 [arXiv]에 게시한 ‘Open Data Synthesis For Deep Research’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mimicking the Physicist’s Eye:A VLM-centric Approach for Physics Formula Discovery

September 1, 2025

Wenjie Zhou이 [arXiv]에 게시한 ‘Mimicking the Physicist’s Eye:A VLM-centric Approach for Physics Formula Discovery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers

September 1, 2025

Jiamin Wu이 [arXiv]에 게시한 ‘A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AWorld: Orchestrating the Training Recipe for Agentic AI

August 29, 2025

Qintong Wu이 [arXiv]에 게시한 ‘AWorld: Orchestrating the Training Recipe for Agentic AI’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Explain Before You Answer: A Survey on Compositional Visual Reasoning

August 26, 2025

Xin Zheng이 [arXiv]에 게시한 ‘Explain Before You Answer: A Survey on Compositional Visual Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery

August 21, 2025

zijieqiu이 [arXiv]에 게시한 ‘From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SSRL: Self-Search Reinforcement Learning

August 18, 2025

Yanxu Chen이 [arXiv]에 게시한 ‘SSRL: Self-Search Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches

August 13, 2025

Qiang Ju이 [arXiv]에 게시한 ‘HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

August 11, 2025

GLM-4. 5 Team이 [arXiv]에 게시한 ‘GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning

August 8, 2025

Ziming Wang이 [arXiv]에 게시한 ‘DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Policy Optimization

[논문리뷰] MAPO: Mixed Advantage Policy Optimization

September 24, 2025

Xuankun Rong이 [arXiv]에 게시한 ‘MAPO: Mixed Advantage Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token’s Nature

September 23, 2025

Bin Cui이 [arXiv]에 게시한 ‘From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token’s Nature’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Inpainting-Guided Policy Optimization for Diffusion Large Language Models

September 15, 2025

Chenyu Wang이 [arXiv]에 게시한 ‘Inpainting-Guided Policy Optimization for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Survey of Reinforcement Learning for Large Reasoning Models

September 11, 2025

Runze Liu이 [arXiv]에 게시한 ‘A Survey of Reinforcement Learning for Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding

September 10, 2025

Yongcheng Zeng이 [arXiv]에 게시한 ‘Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Bootstrapping Task Spaces for Self-Improvement

September 8, 2025

Yoram Bachrach이 [arXiv]에 게시한 ‘Bootstrapping Task Spaces for Self-Improvement’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

September 3, 2025

Hejia Geng이 [arXiv]에 게시한 ‘The Landscape of Agentic Reinforcement Learning for LLMs: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR

September 3, 2025

Lu Wang이 [arXiv]에 게시한 ‘Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DCPO: Dynamic Clipping Policy Optimization

September 3, 2025

Kai Lu이 [arXiv]에 게시한 ‘DCPO: Dynamic Clipping Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning

September 2, 2025

Yuewei Zhang이 [arXiv]에 게시한 ‘PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling

August 27, 2025

Zhoufutu Wen이 [arXiv]에 게시한 ‘TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling’ 논문에 대한 ...

[논문리뷰] Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning

August 26, 2025

Jiale Zhao이 [arXiv]에 게시한 ‘Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models

August 15, 2025

Qinghao Ye이 [arXiv]에 게시한 ‘Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models

August 14, 2025

Guiyang Hou이 [arXiv]에 게시한 ‘Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforcement Learning in Vision: A Survey

August 12, 2025

Qingwei Meng이 [arXiv]에 게시한 ‘Reinforcement Learning in Vision: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning

August 12, 2025

Jiaheng Liu이 [arXiv]에 게시한 ‘Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization

August 12, 2025

Guanting Dong이 [arXiv]에 게시한 ‘Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization

August 11, 2025

Pengxiang Li이 [arXiv]에 게시한 ‘InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning

[논문리뷰] GenExam: A Multidisciplinary Text-to-Image Exam

September 18, 2025

Yu Qiao이 [arXiv]에 게시한 ‘GenExam: A Multidisciplinary Text-to-Image Exam’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DCPO: Dynamic Clipping Policy Optimization

September 3, 2025

Kai Lu이 [arXiv]에 게시한 ‘DCPO: Dynamic Clipping Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning

September 1, 2025

Han Hu이 [arXiv]에 게시한 ‘R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AHELM: A Holistic Evaluation of Audio-Language Models

September 1, 2025

Siwei Yang이 [arXiv]에 게시한 ‘AHELM: A Holistic Evaluation of Audio-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling

August 27, 2025

Zhoufutu Wen이 [arXiv]에 게시한 ‘TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling’ 논문에 대한 ...

[논문리뷰] InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

August 26, 2025

jinglinglin이 [arXiv]에 게시한 ‘InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

August 21, 2025

Guoyin Wang이 [arXiv]에 게시한 ‘On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting’ 논문에 대한...

[논문리뷰] MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence

August 20, 2025

Fernando López이 [arXiv]에 게시한 ‘MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents

August 20, 2025

Jun Dong이 [arXiv]에 게시한 ‘MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs

August 15, 2025

Yi Yuan이 [arXiv]에 게시한 ‘HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance

August 14, 2025

Yong Li이 [arXiv]에 게시한 ‘AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

August 11, 2025

GLM-4. 5 Team이 [arXiv]에 게시한 ‘GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] R-Zero: Self-Evolving Reasoning LLM from Zero Data

August 8, 2025

Zongxia Li이 [arXiv]에 게시한 ‘R-Zero: Self-Evolving Reasoning LLM from Zero Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities

August 8, 2025

Zhijie Sang이 [arXiv]에 게시한 ‘InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following

August 7, 2025

Liang Xu이 [arXiv]에 게시한 ‘Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens

August 7, 2025

Zhen Tan이 [arXiv]에 게시한 ‘Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

August 4, 2025

Hao Tang이 [arXiv]에 게시한 ‘3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Agents

[논문리뷰] ARE: Scaling Up Agent Environments and Evaluations

September 23, 2025

Matteo Bettini이 [arXiv]에 게시한 ‘ARE: Scaling Up Agent Environments and Evaluations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research

September 17, 2025

Houquan Zhou이 [arXiv]에 게시한 ‘WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization

September 17, 2025

Litu Ou이 [arXiv]에 게시한 ‘ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents

September 12, 2025

Xintao Wang이 [arXiv]에 게시한 ‘Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning

September 11, 2025

Honglin Guo이 [arXiv]에 게시한 ‘AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

September 3, 2025

Hejia Geng이 [arXiv]에 게시한 ‘The Landscape of Agentic Reinforcement Learning for LLMs: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench

September 2, 2025

Jayanth Srinivasa이 [arXiv]에 게시한 ‘How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench’ 논문에 대한 자세한 리뷰입...

[논문리뷰] MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

August 29, 2025

Shashank Biju이 [arXiv]에 게시한 ‘MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Training Language Model Agents to Find Vulnerabilities with CTF-Dojo

August 27, 2025

Zijian Wang이 [arXiv]에 게시한 ‘Training Language Model Agents to Find Vulnerabilities with CTF-Dojo’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications

August 25, 2025

Liuyi Yao이 [arXiv]에 게시한 ‘AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

August 21, 2025

tianlecai이 [arXiv]에 게시한 ‘FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents

August 20, 2025

Flora D. Salim이 [arXiv]에 게시한 ‘ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL

August 13, 2025

Chuyi He이 [arXiv]에 게시한 ‘Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Memp: Exploring Agent Procedural Memory

August 11, 2025

Shuofei Qiao이 [arXiv]에 게시한 ‘Memp: Exploring Agent Procedural Memory’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Efficient Agents: Building Effective Agents While Reducing Cost

August 7, 2025

Yue Hou이 [arXiv]에 게시한 ‘Efficient Agents: Building Effective Agents While Reducing Cost’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks

August 5, 2025

Zhiwei Zhang이 [arXiv]에 게시한 ‘AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SWE-Exp: Experience-Driven Software Issue Resolution

August 4, 2025

Heng Lian이 [arXiv]에 게시한 ‘SWE-Exp: Experience-Driven Software Issue Resolution’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Generative AI

[논문리뷰] Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

September 24, 2025

Yifeng Jiang이 [arXiv]에 게시한 ‘Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation

September 17, 2025

Lixin Xu이 [arXiv]에 게시한 ‘Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 3D Aware Region Prompted Vision Language Model

September 17, 2025

Xiaolong Li이 [arXiv]에 게시한 ‘3D Aware Region Prompted Vision Language Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] X-Part: high fidelity and structure coherent shape decomposition

September 15, 2025

Yunhan Yang이 [arXiv]에 게시한 ‘X-Part: high fidelity and structure coherent shape decomposition’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis

September 15, 2025

Song Guo이 [arXiv]에 게시한 ‘InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Jointly Reinforcing Diversity and Quality in Language Model Generations

September 3, 2025

Tianlu이 [arXiv]에 게시한 ‘Jointly Reinforcing Diversity and Quality in Language Model Generations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Dress&Dance: Dress up and Dance as You Like It - Technical Preview

August 29, 2025

Yu-Xiong Wang이 [arXiv]에 게시한 ‘Dress&Dance: Dress up and Dance as You Like It - Technical Preview’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation

August 26, 2025

Haoxiang Shi이 [arXiv]에 게시한 ‘Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TempFlow-GRPO: When Timing Matters for GRPO in Flow Models

August 20, 2025

Jian Yang이 [arXiv]에 게시한 ‘TempFlow-GRPO: When Timing Matters for GRPO in Flow Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniTry: Virtual Try-On Anything without Masks

August 20, 2025

Xiaoduan Feng이 [arXiv]에 게시한 ‘OmniTry: Virtual Try-On Anything without Masks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation

August 18, 2025

Junyong Noh이 [arXiv]에 게시한 ‘StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing

August 15, 2025

Xiaoyu Li이 [arXiv]에 게시한 ‘ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Survey on Diffusion Language Models

August 15, 2025

Zhiqiang Shen이 [arXiv]에 게시한 ‘A Survey on Diffusion Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models

August 14, 2025

Zeynep Akata이 [arXiv]에 게시한 ‘Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future

August 12, 2025

Qiufeng Wang이 [arXiv]에 게시한 ‘Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off

August 11, 2025

jgkwak이 [arXiv]에 게시한 ‘Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Personalized Safety Alignment for Text-to-Image Diffusion Models

August 5, 2025

Kaidong Yu이 [arXiv]에 게시한 ‘Personalized Safety Alignment for Text-to-Image Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Transformer

[논문리뷰] Synthetic bootstrapped pretraining

September 23, 2025

Emmanuel Candès이 [arXiv]에 게시한 ‘Synthetic bootstrapped pretraining’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Cross-Attention is Half Explanation in Speech-to-Text Models

September 23, 2025

Luisa Bentivogli이 [arXiv]에 게시한 ‘Cross-Attention is Half Explanation in Speech-to-Text Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers

September 22, 2025

Karun Kumar이 [arXiv]에 게시한 ‘WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

September 19, 2025

SpaceProduct이 [arXiv]에 게시한 ‘RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Wan-Animate: Unified Character Animation and Replacement with Holistic Replication

September 18, 2025

Mingyang Huang이 [arXiv]에 게시한 ‘Wan-Animate: Unified Character Animation and Replacement with Holistic Replication’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] P3-SAM: Native 3D Part Segmentation

September 11, 2025

Yunhan Yang이 [arXiv]에 게시한 ‘P3-SAM: Native 3D Part Segmentation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Causal Attention with Lookahead Keys

September 10, 2025

Quanquan Gu이 [arXiv]에 게시한 ‘Causal Attention with Lookahead Keys’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Multi-View 3D Point Tracking

August 29, 2025

Irem Demir이 [arXiv]에 게시한 ‘Multi-View 3D Point Tracking’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Predicting the Order of Upcoming Tokens Improves Language Modeling

August 28, 2025

Alham Fikri Aji이 [arXiv]에 게시한 ‘Predicting the Order of Upcoming Tokens Improves Language Modeling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies

August 28, 2025

Sitong Mao이 [arXiv]에 게시한 ‘Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Waver: Wave Your Way to Lifelike Video Generation

August 22, 2025

Yifu Zhang이 [arXiv]에 게시한 ‘Waver: Wave Your Way to Lifelike Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass

August 22, 2025

Ya Zhang이 [arXiv]에 게시한 ‘SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VertexRegen: Mesh Generation with Continuous Level of Detail

August 13, 2025

Jakob Engel이 [arXiv]에 게시한 ‘VertexRegen: Mesh Generation with Continuous Level of Detail’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GLiClass: Generalist Lightweight Model for Sequence Classification Tasks

August 12, 2025

Alexander Yavorskyi이 [arXiv]에 게시한 ‘GLiClass: Generalist Lightweight Model for Sequence Classification Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets

August 7, 2025

MaziyarPanahi이 [arXiv]에 게시한 ‘OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets’ 논문에 대한 자세한 ...

[논문리뷰] LeanK: Learnable K Cache Channel Pruning for Efficient Decoding

August 7, 2025

Yuqing Yang이 [arXiv]에 게시한 ‘LeanK: Learnable K Cache Channel Pruning for Efficient Decoding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer

August 6, 2025

Shunyu Yao이 [arXiv]에 게시한 ‘LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reinforcement Learning (RL)

[논문리뷰] GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning

September 23, 2025

Hou Pong Chan이 [arXiv]에 게시한 ‘GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning

September 22, 2025

Jiangmiao이 [arXiv]에 게시한 ‘A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Improving Context Fidelity via Native Retrieval-Augmented Reasoning

September 18, 2025

Xiangru Tang이 [arXiv]에 게시한 ‘Improving Context Fidelity via Native Retrieval-Augmented Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual Programmability: A Guide for Code-as-Thought in Chart Understanding

September 12, 2025

Ethan Chern이 [arXiv]에 게시한 ‘Visual Programmability: A Guide for Code-as-Thought in Chart Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

September 12, 2025

Zhaohui Yang이 [arXiv]에 게시한 ‘SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents

September 9, 2025

Aili Chen이 [arXiv]에 게시한 ‘WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers

September 9, 2025

Xia Xiao이 [arXiv]에 게시한 ‘Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Bootstrapping Task Spaces for Self-Improvement

September 8, 2025

Yoram Bachrach이 [arXiv]에 게시한 ‘Bootstrapping Task Spaces for Self-Improvement’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Towards a Unified View of Large Language Model Post-Training

September 5, 2025

Hongyi Liu이 [arXiv]에 게시한 ‘Towards a Unified View of Large Language Model Post-Training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Robix: A Unified Model for Robot Interaction, Reasoning and Planning

September 4, 2025

Zixuan Wang이 [arXiv]에 게시한 ‘Robix: A Unified Model for Robot Interaction, Reasoning and Planning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

September 3, 2025

Jianwei Yang이 [arXiv]에 게시한 ‘LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning

September 1, 2025

Han Hu이 [arXiv]에 게시한 ‘R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments

August 13, 2025

Xuesong Yao이 [arXiv]에 게시한 ‘Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforcement Learning in Vision: A Survey

August 12, 2025

Qingwei Meng이 [arXiv]에 게시한 ‘Reinforcement Learning in Vision: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

August 8, 2025

Xinyu Ye이 [arXiv]에 게시한 ‘On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Tool-integrated Reinforcement Learning for Repo Deep Search

August 6, 2025

Yanzhen Zou이 [arXiv]에 게시한 ‘Tool-integrated Reinforcement Learning for Repo Deep Search’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM

[논문리뷰] EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving

September 17, 2025

Shansan Gong이 [arXiv]에 게시한 ‘EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation

September 16, 2025

Heshaam Faili이 [arXiv]에 게시한 ‘SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering

September 15, 2025

Zhehao Tan이 [arXiv]에 게시한 ‘HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem

September 9, 2025

Damien Sileo이 [arXiv]에 게시한 ‘Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DCPO: Dynamic Clipping Policy Optimization

September 3, 2025

Kai Lu이 [arXiv]에 게시한 ‘DCPO: Dynamic Clipping Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Baichuan-M2: Scaling Medical Capability with Large Verifier System

September 3, 2025

Jayok6이 [arXiv]에 게시한 ‘Baichuan-M2: Scaling Medical Capability with Large Verifier System’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

August 21, 2025

Jiangmiao이 [arXiv]에 게시한 ‘MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping

August 19, 2025

Tyler Derr이 [arXiv]에 게시한 ‘Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving

August 14, 2025

Jinjie Gu이 [arXiv]에 게시한 ‘AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WideSearch: Benchmarking Agentic Broad Info-Seeking

August 12, 2025

Yan Gao이 [arXiv]에 게시한 ‘WideSearch: Benchmarking Agentic Broad Info-Seeking’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks

August 12, 2025

Hongxing Li이 [arXiv]에 게시한 ‘OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Compressing Chain-of-Thought in LLMs via Step Entropy

August 12, 2025

Zhijian Xu이 [arXiv]에 게시한 ‘Compressing Chain-of-Thought in LLMs via Step Entropy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

August 8, 2025

Xinyu Ye이 [arXiv]에 게시한 ‘On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LeanK: Learnable K Cache Channel Pruning for Efficient Decoding

August 7, 2025

Yuqing Yang이 [arXiv]에 게시한 ‘LeanK: Learnable K Cache Channel Pruning for Efficient Decoding’ 논문에 대한 자세한 리뷰입니다.

[LLM] LLM을 활용한 코드 리뷰

January 3, 2025

github workflow를 활용해 코드 리뷰를 자동화하기

Back to Top ↑

Image Generation

[논문리뷰] CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching

September 24, 2025

Rui Qian이 [arXiv]에 게시한 ‘CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

September 23, 2025

Qinsheng Zhang이 [arXiv]에 게시한 ‘DiffusionNFT: Online Diffusion Reinforcement with Forward Process’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

September 22, 2025

Wenyu Wang이 [arXiv]에 게시한 ‘Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation

September 19, 2025

Xihui Liu이 [arXiv]에 게시한 ‘Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks

September 19, 2025

Xijun Gu이 [arXiv]에 게시한 ‘MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reconstruction Alignment Improves Unified Multimodal Models

September 10, 2025

XuDong Wang이 [arXiv]에 게시한 ‘Reconstruction Alignment Improves Unified Multimodal Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Transition Models: Rethinking the Generative Learning Objective

September 5, 2025

Yangguang Li이 [arXiv]에 게시한 ‘Transition Models: Rethinking the Generative Learning Objective’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation

September 4, 2025

Kai Li이 [arXiv]에 게시한 ‘Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning

August 29, 2025

Yitong Wang이 [arXiv]에 게시한 ‘OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CineScale: Free Lunch in High-Resolution Cinematic Visual Generation

August 27, 2025

Ziwei Liu이 [arXiv]에 게시한 ‘CineScale: Free Lunch in High-Resolution Cinematic Visual Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Next Visual Granularity Generation

August 19, 2025

Kang Liao이 [arXiv]에 게시한 ‘Next Visual Granularity Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation

August 14, 2025

Zhenghao Hu이 [arXiv]에 게시한 ‘Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents

August 12, 2025

Mohit Bansal이 [arXiv]에 게시한 ‘Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation

August 6, 2025

Tianyidan Xie이 [arXiv]에 게시한 ‘Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Qwen-Image Technical Report

August 5, 2025

Kaiyuan Gao이 [arXiv]에 게시한 ‘Qwen-Image Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Benchmarking

[논문리뷰] WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning

September 8, 2025

Amit Namburi이 [arXiv]에 게시한 ‘WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MobiAgent: A Systematic Framework for Customizable Mobile Agents

September 3, 2025

Wangbo Gong이 [arXiv]에 게시한 ‘MobiAgent: A Systematic Framework for Customizable Mobile Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Benchmarking Optimizers for Large Language Model Pretraining

September 3, 2025

mjaggi이 [arXiv]에 게시한 ‘Benchmarking Optimizers for Large Language Model Pretraining’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AHELM: A Holistic Evaluation of Audio-Language Models

September 1, 2025

Siwei Yang이 [arXiv]에 게시한 ‘AHELM: A Holistic Evaluation of Audio-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

August 29, 2025

Shashank Biju이 [arXiv]에 게시한 ‘MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents

August 28, 2025

Yue Yao이 [arXiv]에 게시한 ‘Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries

August 22, 2025

huuuyeah이 [arXiv]에 게시한 ‘LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers

August 21, 2025

Prathyusha Jwalapuram이 [arXiv]에 게시한 ‘MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation

August 14, 2025

Zhenghao Hu이 [arXiv]에 게시한 ‘Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks

August 12, 2025

Hongxing Li이 [arXiv]에 게시한 ‘OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

August 12, 2025

Kai Zou이 [arXiv]에 게시한 ‘BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations

August 8, 2025

Chirag Shah이 [arXiv]에 게시한 ‘I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations’ 논문에...

[논문리뷰] CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward

August 6, 2025

Songyang Gao이 [arXiv]에 게시한 ‘CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AgroBench: Vision-Language Model Benchmark in Agriculture

August 3, 2025

Yoshitaka Ushiku이 [arXiv]에 게시한 ‘AgroBench: Vision-Language Model Benchmark in Agriculture’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Embodied AI

[논문리뷰] Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue

September 22, 2025

Hui Zhang이 [arXiv]에 게시한 ‘Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era

September 18, 2025

Zihao Dongfang이 [arXiv]에 게시한 ‘PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts

September 16, 2025

Wenzhe Cai이 [arXiv]에 게시한 ‘InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning

September 12, 2025

Yuzheng Zhuang이 [arXiv]에 게시한 ‘OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions

September 10, 2025

Zherui Qiu이 [arXiv]에 게시한 ‘F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Robix: A Unified Model for Robot Interaction, Reasoning and Planning

September 4, 2025

Zixuan Wang이 [arXiv]에 게시한 ‘Robix: A Unified Model for Robot Interaction, Reasoning and Planning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control

September 1, 2025

Zhaoqing Chen이 [arXiv]에 게시한 ‘EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RynnEC: Bringing MLLMs into Embodied World

August 21, 2025

jiangpinliu이 [arXiv]에 게시한 ‘RynnEC: Bringing MLLMs into Embodied World’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation

August 20, 2025

Fei Ni이 [arXiv]에 게시한 ‘Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks

August 12, 2025

Hongxing Li이 [arXiv]에 게시한 ‘OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation

August 8, 2025

Shengcong Chen이 [arXiv]에 게시한 ‘Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success

August 7, 2025

Ruslan Rakhimov이 [arXiv]에 게시한 ‘Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success’ 논문에 대한 자세한 리뷰...

[논문리뷰] RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Lifelong Learning in Physical Embodied Systems

August 5, 2025

Junkun Hong이 [arXiv]에 게시한 ‘RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Lifelong Learning in Physical Embodied Systems’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation

August 4, 2025

Jianjiang Feng이 [arXiv]에 게시한 ‘IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Code Generation

[논문리뷰] SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

September 23, 2025

Yannis Yiming He이 [arXiv]에 게시한 ‘SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation

September 22, 2025

Steven Liu이 [arXiv]에 게시한 ‘RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning

September 18, 2025

Yicheng Pan이 [arXiv]에 게시한 ‘THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning

September 18, 2025

Zhou Yang이 [arXiv]에 게시한 ‘Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

September 9, 2025

Ke Shen이 [arXiv]에 게시한 ‘Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Universal Deep Research: Bring Your Own Model and Strategy

September 3, 2025

Pavlo Molchanov이 [arXiv]에 게시한 ‘Universal Deep Research: Bring Your Own Model and Strategy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Thyme: Think Beyond Images

August 18, 2025

Wei Chen이 [arXiv]에 게시한 ‘Thyme: Think Beyond Images’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models

August 14, 2025

Dongdong Zhang이 [arXiv]에 게시한 ‘VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization

August 12, 2025

Guanting Dong이 [arXiv]에 게시한 ‘Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

August 11, 2025

GLM-4. 5 Team이 [arXiv]에 게시한 ‘GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CoAct-1: Computer-using Agents with Coding as Actions

August 8, 2025

Taiwei Shi이 [arXiv]에 게시한 ‘CoAct-1: Computer-using Agents with Coding as Actions’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LaTCoder: Converting Webpage Design to Code with Layout-as-Thought

August 7, 2025

Tianpeng Lv이 [arXiv]에 게시한 ‘LaTCoder: Converting Webpage Design to Code with Layout-as-Thought’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

August 6, 2025

Fan Xia이 [arXiv]에 게시한 ‘Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CellForge: Agentic Design of Virtual Cell Models

August 5, 2025

Daniel Shao이 [arXiv]에 게시한 ‘CellForge: Agentic Design of Virtual Cell Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-to-Image Generation

[논문리뷰] Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation

September 24, 2025

Jianbin Zheng이 [arXiv]에 게시한 ‘Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

September 22, 2025

jialingt이 [arXiv]에 게시한 ‘MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GenExam: A Multidisciplinary Text-to-Image Exam

September 18, 2025

Yu Qiao이 [arXiv]에 게시한 ‘GenExam: A Multidisciplinary Text-to-Image Exam’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark

September 12, 2025

Shuai Bai이 [arXiv]에 게시한 ‘FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

September 10, 2025

Yingfang Zhang이 [arXiv]에 게시한 ‘Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Interleaving Reasoning for Better Text-to-Image Generation

September 9, 2025

Shixiang Tang이 [arXiv]에 게시한 ‘Interleaving Reasoning for Better Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?

September 9, 2025

Rui Chen이 [arXiv]에 게시한 ‘Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

August 29, 2025

Jiazi Bu이 [arXiv]에 게시한 ‘Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation

August 26, 2025

Haoxiang Shi이 [arXiv]에 게시한 ‘Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation

August 26, 2025

Xihui Liu이 [arXiv]에 게시한 ‘T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

August 15, 2025

Quan Sun이 [arXiv]에 게시한 ‘NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation

August 13, 2025

Kevin Galim이 [arXiv]에 게시한 ‘UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models

August 7, 2025

Elisabetta Rocchetti이 [arXiv]에 게시한 ‘The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HPSv3: Towards Wide-Spectrum Human Preference Score

August 7, 2025

Hongsheng Li이 [arXiv]에 게시한 ‘HPSv3: Towards Wide-Spectrum Human Preference Score’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Foundation Models

[논문리뷰] MAPO: Mixed Advantage Policy Optimization

September 24, 2025

Xuankun Rong이 [arXiv]에 게시한 ‘MAPO: Mixed Advantage Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LIMI: Less is More for Agency

September 23, 2025

happyZYM이 [arXiv]에 게시한 ‘LIMI: Less is More for Agency’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios

September 15, 2025

Bing Su이 [arXiv]에 게시한 ‘LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual Representation Alignment for Multimodal Large Language Models

September 10, 2025

Heeseong Shin이 [arXiv]에 게시한 ‘Visual Representation Alignment for Multimodal Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UniVerse-1: Unified Audio-Video Generation via Stitching of Experts

September 9, 2025

Xinyao Liao이 [arXiv]에 게시한 ‘UniVerse-1: Unified Audio-Video Generation via Stitching of Experts’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Does DINOv3 Set a New Medical Vision Standard?

September 9, 2025

Bailiang Jian이 [arXiv]에 게시한 ‘Does DINOv3 Set a New Medical Vision Standard?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision

September 3, 2025

Yan-Jie Zhou이 [arXiv]에 게시한 ‘M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control

September 1, 2025

Zhaoqing Chen이 [arXiv]에 게시한 ‘EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations

August 20, 2025

Mounia Lalmas이 [arXiv]에 게시한 ‘Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DINOv3

August 18, 2025

Maxime Oquab이 [arXiv]에 게시한 ‘DINOv3’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Processing and acquisition traces in visual encoders: What does CLIP know about your camera?

August 15, 2025

Giorgos Tolias이 [arXiv]에 게시한 ‘Processing and acquisition traces in visual encoders: What does CLIP know about your camera?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

August 12, 2025

Xinhao Yi이 [arXiv]에 게시한 ‘A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems’ 논문에 대한 자세...

[논문리뷰] villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models

August 3, 2025

Kaixin Wang이 [arXiv]에 게시한 ‘villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Robotics

[논문리뷰] ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces

September 23, 2025

Jiafeng Xu이 [arXiv]에 게시한 ‘ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning

September 22, 2025

Jiangmiao이 [arXiv]에 게시한 ‘A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies

September 15, 2025

Fabian Otto이 [arXiv]에 게시한 ‘FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

September 12, 2025

Zirui Ge이 [arXiv]에 게시한 ‘VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning

September 12, 2025

Yuzheng Zhuang이 [arXiv]에 게시한 ‘OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 3D and 4D World Modeling: A Survey

September 11, 2025

Ao Liang이 [arXiv]에 게시한 ‘3D and 4D World Modeling: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Robix: A Unified Model for Robot Interaction, Reasoning and Planning

September 4, 2025

Zixuan Wang이 [arXiv]에 게시한 ‘Robix: A Unified Model for Robot Interaction, Reasoning and Planning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification

August 29, 2025

Liqiang Nie이 [arXiv]에 게시한 ‘CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Do What? Teaching Vision-Language-Action Models to Reject the Impossible

August 25, 2025

Roei Herzig이 [arXiv]에 게시한 ‘Do What? Teaching Vision-Language-Action Models to Reject the Impossible’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RynnEC: Bringing MLLMs into Embodied World

August 21, 2025

jiangpinliu이 [arXiv]에 게시한 ‘RynnEC: Bringing MLLMs into Embodied World’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MolmoAct: Action Reasoning Models that can Reason in Space

August 12, 2025

Shuo Liu이 [arXiv]에 게시한 ‘MolmoAct: Action Reasoning Models that can Reason in Space’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Lifelong Learning in Physical Embodied Systems

August 5, 2025

Junkun Hong이 [arXiv]에 게시한 ‘RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Lifelong Learning in Physical Embodied Systems’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation

August 4, 2025

Jianjiang Feng이 [arXiv]에 게시한 ‘IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Curation

[논문리뷰] LIMI: Less is More for Agency

September 23, 2025

happyZYM이 [arXiv]에 게시한 ‘LIMI: Less is More for Agency’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] BaseReward: A Strong Baseline for Multimodal Reward Model

September 22, 2025

jianfeipan이 [arXiv]에 게시한 ‘BaseReward: A Strong Baseline for Multimodal Reward Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SAIL-VL2 Technical Report

September 18, 2025

Zijian Kang이 [arXiv]에 게시한 ‘SAIL-VL2 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval

September 12, 2025

Kaicheng Yang이 [arXiv]에 게시한 ‘Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge

September 10, 2025

Dipanjan Das이 [arXiv]에 게시한 ‘SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis

September 1, 2025

Pengcheng Chen이 [arXiv]에 게시한 ‘TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Wan-S2V: Audio-Driven Cinematic Video Generation

August 27, 2025

Chaonan Ji이 [arXiv]에 게시한 ‘Wan-S2V: Audio-Driven Cinematic Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Waver: Wave Your Way to Lifelike Video Generation

August 22, 2025

Yifu Zhang이 [arXiv]에 게시한 ‘Waver: Wave Your Way to Lifelike Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Intern-S1: A Scientific Multimodal Foundation Model

August 22, 2025

xuhuang87이 [arXiv]에 게시한 ‘Intern-S1: A Scientific Multimodal Foundation Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models

August 22, 2025

Lifan Guo이 [arXiv]에 게시한 ‘Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TexVerse: A Universe of 3D Objects with High-Resolution Textures

August 18, 2025

Nan Cao이 [arXiv]에 게시한 ‘TexVerse: A Universe of 3D Objects with High-Resolution Textures’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities

August 8, 2025

Zhijie Sang이 [arXiv]에 게시한 ‘InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MiDashengLM: Efficient Audio Understanding with General Audio Captions

August 7, 2025

Yadong Niu이 [arXiv]에 게시한 ‘MiDashengLM: Efficient Audio Understanding with General Audio Captions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal LLMs

[논문리뷰] VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction

September 24, 2025

So Fukuda이 [arXiv]에 게시한 ‘VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

September 23, 2025

Shaohui Jiao이 [arXiv]에 게시한 ‘TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning

September 12, 2025

Yuzheng Zhuang이 [arXiv]에 게시한 ‘OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual Representation Alignment for Multimodal Large Language Models

September 10, 2025

Heeseong Shin이 [arXiv]에 게시한 ‘Visual Representation Alignment for Multimodal Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforced Visual Perception with Tools

September 9, 2025

Mingyang Fu이 [arXiv]에 게시한 ‘Reinforced Visual Perception with Tools’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Kwai Keye-VL 1.5 Technical Report

September 3, 2025

SXxtyz이 [arXiv]에 게시한 ‘Kwai Keye-VL 1.5 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation

August 26, 2025

Haoxiang Shi이 [arXiv]에 게시한 ‘Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Ovis2.5 Technical Report

August 19, 2025

Yang Li이 [arXiv]에 게시한 ‘Ovis2.5 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Has GPT-5 Achieved Spatial Intelligence? An Empirical Study

August 19, 2025

Ruisi Wang이 [arXiv]에 게시한 ‘Has GPT-5 Achieved Spatial Intelligence? An Empirical Study’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Thyme: Think Beyond Images

August 18, 2025

Wei Chen이 [arXiv]에 게시한 ‘Thyme: Think Beyond Images’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Controlling Multimodal LLMs via Reward-guided Decoding

August 18, 2025

Michal Drozdzal이 [arXiv]에 게시한 ‘Controlling Multimodal LLMs via Reward-guided Decoding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs

August 15, 2025

Yi Yuan이 [arXiv]에 게시한 ‘HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?

August 8, 2025

Junjie Yang이 [arXiv]에 게시한 ‘Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Computational Efficiency

[논문리뷰] Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation

September 24, 2025

Jianbin Zheng이 [arXiv]에 게시한 ‘Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs

September 23, 2025

Anand Mishra이 [arXiv]에 게시한 ‘When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs’ 논문에...

[논문리뷰] CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification

August 29, 2025

Liqiang Nie이 [arXiv]에 게시한 ‘CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models

August 27, 2025

Jiangjie Chen이 [arXiv]에 게시한 ‘ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Deep Think with Confidence

August 22, 2025

Xuewei Wang이 [arXiv]에 게시한 ‘Deep Think with Confidence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping

August 19, 2025

Tyler Derr이 [arXiv]에 게시한 ‘Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GLiClass: Generalist Lightweight Model for Sequence Classification Tasks

August 12, 2025

Alexander Yavorskyi이 [arXiv]에 게시한 ‘GLiClass: Generalist Lightweight Model for Sequence Classification Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models

August 5, 2025

Zuxuan Wu이 [arXiv]에 게시한 ‘A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges

August 4, 2025

Chengfei Lv이 [arXiv]에 게시한 ‘Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models

August 4, 2025

Jiaqi Wang이 [arXiv]에 게시한 ‘Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Phi-Ground Tech Report: Advancing Perception in GUI Grounding

August 3, 2025

Kai Qiu이 [arXiv]에 게시한 ‘Phi-Ground Tech Report: Advancing Perception in GUI Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Efficient Machine Unlearning via Influence Approximation

August 3, 2025

Enhong Chen이 [arXiv]에 게시한 ‘Efficient Machine Unlearning via Influence Approximation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Generalization

[논문리뷰] A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning

September 22, 2025

Jiangmiao이 [arXiv]에 게시한 ‘A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

September 12, 2025

Zhaohui Yang이 [arXiv]에 게시한 ‘SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions

September 10, 2025

Zherui Qiu이 [arXiv]에 게시한 ‘F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On Robustness and Reliability of Benchmark-Based Evaluation of LLMs

September 8, 2025

Kevin Roitero이 [arXiv]에 게시한 ‘On Robustness and Reliability of Benchmark-Based Evaluation of LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control

September 1, 2025

Zhaoqing Chen이 [arXiv]에 게시한 ‘EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

August 28, 2025

Jianze Liang이 [arXiv]에 게시한 ‘CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning’ 논문에 대한 ...

[논문리뷰] Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling

August 26, 2025

Daniil Orel이 [arXiv]에 게시한 ‘Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation

August 20, 2025

Jonas Geiping이 [arXiv]에 게시한 ‘MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation

August 12, 2025

Hengtao Shen이 [arXiv]에 게시한 ‘Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

August 8, 2025

Xinyu Ye이 [arXiv]에 게시한 ‘On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents

August 3, 2025

Anji Liu이 [arXiv]에 게시한 ‘Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Flow Equivariant Recurrent Neural Networks

August 3, 2025

T. Anderson Keller이 [arXiv]에 게시한 ‘Flow Equivariant Recurrent Neural Networks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Instruction Following

[논문리뷰] FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions

September 23, 2025

tengdai722이 [arXiv]에 게시한 ‘FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questio...

[논문리뷰] Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems

September 22, 2025

Hung-yi Lee이 [arXiv]에 게시한 ‘Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems’ 논문에 대...

[논문리뷰] Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue

September 22, 2025

Hui Zhang이 [arXiv]에 게시한 ‘Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RecoWorld: Building Simulated Environments for Agentic Recommender Systems

September 19, 2025

Mingyuan Wu이 [arXiv]에 게시한 ‘RecoWorld: Building Simulated Environments for Agentic Recommender Systems’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Language Self-Play For Data-Free Training

September 10, 2025

Vijai Mohan이 [arXiv]에 게시한 ‘Language Self-Play For Data-Free Training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?

September 5, 2025

Yu Fu이 [arXiv]에 게시한 ‘Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Do What? Teaching Vision-Language-Action Models to Reject the Impossible

August 25, 2025

Roei Herzig이 [arXiv]에 게시한 ‘Do What? Teaching Vision-Language-Action Models to Reject the Impossible’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

August 21, 2025

abercovich이 [arXiv]에 게시한 ‘NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation

August 14, 2025

Zhenghao Hu이 [arXiv]에 게시한 ‘Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following

August 7, 2025

Liang Xu이 [arXiv]에 게시한 ‘Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards

August 7, 2025

Ling-I Wu이 [arXiv]에 게시한 ‘IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models’ Instruction Following

August 5, 2025

Jiaqing Liang이 [arXiv]에 게시한 ‘Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models’ Instruction Following’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Training-Free

[논문리뷰] ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment

September 23, 2025

Yue Ma이 [arXiv]에 게시한 ‘ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence

September 16, 2025

Lionel M. Ni이 [arXiv]에 게시한 ‘LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Focusing by Contrastive Attention: Enhancing VLMs’ Visual Reasoning

September 9, 2025

Baolong Bi이 [arXiv]에 게시한 ‘Focusing by Contrastive Attention: Enhancing VLMs’ Visual Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Diffusion Language Models Know the Answer Before Decoding

August 28, 2025

Shilin Yan이 [arXiv]에 게시한 ‘Diffusion Language Models Know the Answer Before Decoding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space

August 27, 2025

Rui Chen이 [arXiv]에 게시한 ‘VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer

August 20, 2025

Deyu Zhou이 [arXiv]에 게시한 ‘Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation

August 20, 2025

Jonas Geiping이 [arXiv]에 게시한 ‘MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models

August 19, 2025

Meiqi Wu이 [arXiv]에 게시한 ‘S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Story2Board: A Training-Free Approach for Expressive Storyboard Generation

August 14, 2025

Dani Lischinski이 [arXiv]에 게시한 ‘Story2Board: A Training-Free Approach for Expressive Storyboard Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation

August 13, 2025

Kevin Galim이 [arXiv]에 게시한 ‘UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning

August 12, 2025

Baihong Yuan이 [arXiv]에 게시한 ‘Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer

August 6, 2025

Shunyu Yao이 [arXiv]에 게시한 ‘LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Transformer Architecture

[논문리뷰] AToken: A Unified Tokenizer for Vision

September 19, 2025

Mingze Xu이 [arXiv]에 게시한 ‘AToken: A Unified Tokenizer for Vision’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis

September 15, 2025

Song Guo이 [arXiv]에 게시한 ‘InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings

September 5, 2025

Meie Fang이 [arXiv]에 게시한 ‘Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment

August 28, 2025

An-An Liu이 [arXiv]에 게시한 ‘MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Wan-S2V: Audio-Driven Cinematic Video Generation

August 27, 2025

Chaonan Ji이 [arXiv]에 게시한 ‘Wan-S2V: Audio-Driven Cinematic Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning

August 27, 2025

Ran Guo이 [arXiv]에 게시한 ‘UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Advances in Speech Separation: Techniques, Challenges, and Future Trends

August 20, 2025

Zhuo Chen이 [arXiv]에 게시한 ‘Advances in Speech Separation: Techniques, Challenges, and Future Trends’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

August 15, 2025

Quan Sun이 [arXiv]에 게시한 ‘NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Exploitation Is All You Need… for Exploration

August 5, 2025

Jesse Roberts이 [arXiv]에 게시한 ‘Exploitation Is All You Need… for Exploration’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PixNerd: Pixel Neural Field Diffusion

August 4, 2025

Limin Wang이 [arXiv]에 게시한 ‘PixNerd: Pixel Neural Field Diffusion’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] iLRM: An Iterative Large 3D Reconstruction Model

August 3, 2025

Abdelrahman Mohamed이 [arXiv]에 게시한 ‘iLRM: An Iterative Large 3D Reconstruction Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Deep Learning

[논문리뷰] Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

September 22, 2025

Wenyu Wang이 [arXiv]에 게시한 ‘Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection

September 19, 2025

Zhewei Zhang이 [arXiv]에 게시한 ‘FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] P3-SAM: Native 3D Part Segmentation

September 11, 2025

Yunhan Yang이 [arXiv]에 게시한 ‘P3-SAM: Native 3D Part Segmentation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes

September 2, 2025

Danijel Skočaj이 [arXiv]에 게시한 ‘No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Gaze into the Heart: A Multi-View Video Dataset for rPPG and Health Biomarkers Estimation

August 28, 2025

Anton Ivaschenko이 [arXiv]에 게시한 ‘Gaze into the Heart: A Multi-View Video Dataset for rPPG and Health Biomarkers Estimation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Autoregressive Universal Video Segmentation Model

August 27, 2025

Albert Gu이 [arXiv]에 게시한 ‘Autoregressive Universal Video Segmentation Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration

August 19, 2025

Evgeny Burnaev이 [arXiv]에 게시한 ‘G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion

August 13, 2025

Rachid Nedjai이 [arXiv]에 게시한 ‘WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion’ 논문에 대...

[논문리뷰] MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs

August 12, 2025

Jianguo Li이 [arXiv]에 게시한 ‘MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IAUNet: Instance-Aware U-Net

August 7, 2025

Dmytro Fishman이 [arXiv]에 게시한 ‘IAUNet: Instance-Aware U-Net’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CellForge: Agentic Design of Virtual Cell Models

August 5, 2025

Daniel Shao이 [arXiv]에 게시한 ‘CellForge: Agentic Design of Virtual Cell Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Retrieval-Augmented Generation

[논문리뷰] SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation

September 16, 2025

Heshaam Faili이 [arXiv]에 게시한 ‘SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering

September 15, 2025

Zhehao Tan이 [arXiv]에 게시한 ‘HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Efficient Code Embeddings from Code Generation Models

September 1, 2025

Han Xiao이 [arXiv]에 게시한 ‘Efficient Code Embeddings from Code Generation Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Provable Benefits of In-Tool Learning for Large Language Models

August 29, 2025

Vivien Cabannes이 [arXiv]에 게시한 ‘Provable Benefits of In-Tool Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis

August 28, 2025

Ion Stoica이 [arXiv]에 게시한 ‘DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents

August 20, 2025

Flora D. Salim이 [arXiv]에 게시한 ‘ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

August 12, 2025

Tong Yu이 [arXiv]에 게시한 ‘VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction

August 8, 2025

Prajit Das이 [arXiv]에 게시한 ‘PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?

August 8, 2025

Junjie Yang이 [arXiv]에 게시한 ‘Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search

August 6, 2025

Jiwei Li이 [arXiv]에 게시한 ‘CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CellForge: Agentic Design of Virtual Cell Models

August 5, 2025

Daniel Shao이 [arXiv]에 게시한 ‘CellForge: Agentic Design of Virtual Cell Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Flow Matching

[논문리뷰] CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching

September 24, 2025

Rui Qian이 [arXiv]에 게시한 ‘CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

September 23, 2025

Qinsheng Zhang이 [arXiv]에 게시한 ‘DiffusionNFT: Online Diffusion Reinforcement with Forward Process’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

September 22, 2025

Wenyu Wang이 [arXiv]에 게시한 ‘Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From Editor to Dense Geometry Estimator

September 5, 2025

Lang Nie이 [arXiv]에 게시한 ‘From Editor to Dense Geometry Estimator’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control

September 1, 2025

Zhaoqing Chen이 [arXiv]에 게시한 ‘EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning

August 29, 2025

Yitong Wang이 [arXiv]에 게시한 ‘OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TempFlow-GRPO: When Timing Matters for GRPO in Flow Models

August 20, 2025

Jian Yang이 [arXiv]에 게시한 ‘TempFlow-GRPO: When Timing Matters for GRPO in Flow Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

August 15, 2025

Quan Sun이 [arXiv]에 게시한 ‘NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Marco-Voice Technical Report

August 8, 2025

Qingjuan Li이 [arXiv]에 게시한 ‘Marco-Voice Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering

August 7, 2025

Ambuj Mehrish이 [arXiv]에 게시한 ‘SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation

August 5, 2025

Yang Tian이 [arXiv]에 게시한 ‘InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Contrastive Learning

[논문리뷰] Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation

September 19, 2025

Xihui Liu이 [arXiv]에 게시한 ‘Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation

September 12, 2025

Dong-Ho Lee이 [arXiv]에 게시한 ‘Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Focusing by Contrastive Attention: Enhancing VLMs’ Visual Reasoning

September 9, 2025

Baolong Bi이 [arXiv]에 게시한 ‘Focusing by Contrastive Attention: Enhancing VLMs’ Visual Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings

September 5, 2025

Oren Glickman이 [arXiv]에 게시한 ‘NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Efficient Code Embeddings from Code Generation Models

September 1, 2025

Han Xiao이 [arXiv]에 게시한 ‘Efficient Code Embeddings from Code Generation Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Selective Contrastive Learning for Weakly Supervised Affordance Grounding

August 25, 2025

Jae-Pil Heo이 [arXiv]에 게시한 ‘Selective Contrastive Learning for Weakly Supervised Affordance Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning

August 25, 2025

Yulun Zhang이 [arXiv]에 게시한 ‘CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning’ 논문에 대한 자세한 리뷰...

[논문리뷰] Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation

August 21, 2025

Shiqing Wu이 [arXiv]에 게시한 ‘Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation

August 13, 2025

Kevin Galim이 [arXiv]에 게시한 ‘UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Marco-Voice Technical Report

August 8, 2025

Qingjuan Li이 [arXiv]에 게시한 ‘Marco-Voice Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search

August 6, 2025

Jiwei Li이 [arXiv]에 게시한 ‘CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dataset

[논문리뷰] MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks

September 19, 2025

Xijun Gu이 [arXiv]에 게시한 ‘MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China

September 15, 2025

XU Han이 [arXiv]에 게시한 ‘CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement

September 4, 2025

Hualiang Wang이 [arXiv]에 게시한 ‘MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MultiRef: Controllable Image Generation with Multiple Visual References

August 20, 2025

Shiyun Lang이 [arXiv]에 게시한 ‘MultiRef: Controllable Image Generation with Multiple Visual References’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 4DNeX: Feed-Forward 4D Generative Modeling Made Easy

August 19, 2025

Zeng Tao이 [arXiv]에 게시한 ‘4DNeX: Feed-Forward 4D Generative Modeling Made Easy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models

August 14, 2025

Zhihan Zhou이 [arXiv]에 게시한 ‘MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models’ 논문에 대한 자세한 리뷰...

[논문리뷰] Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation

August 14, 2025

Zhenghao Hu이 [arXiv]에 게시한 ‘Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Matrix-3D: Omnidirectional Explorable 3D World Generation

August 13, 2025

Yuqi Li이 [arXiv]에 게시한 ‘Matrix-3D: Omnidirectional Explorable 3D World Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes

August 8, 2025

Xudong Jiang이 [arXiv]에 게시한 ‘MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HPSv3: Towards Wide-Spectrum Human Preference Score

August 7, 2025

Hongsheng Li이 [arXiv]에 게시한 ‘HPSv3: Towards Wide-Spectrum Human Preference Score’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Multi-human Interactive Talking Dataset

August 6, 2025

Mike Zheng Shou이 [arXiv]에 게시한 ‘Multi-human Interactive Talking Dataset’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mathematical Reasoning

[논문리뷰] SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning

September 23, 2025

Zhaopeng Tu이 [arXiv]에 게시한 ‘SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning

September 18, 2025

Yicheng Pan이 [arXiv]에 게시한 ‘THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Inpainting-Guided Policy Optimization for Diffusion Large Language Models

September 15, 2025

Chenyu Wang이 [arXiv]에 게시한 ‘Inpainting-Guided Policy Optimization for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

September 10, 2025

Xinyu Yang이 [arXiv]에 게시한 ‘Parallel-R1: Towards Parallel Thinking via Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem

September 9, 2025

Damien Sileo이 [arXiv]에 게시한 ‘Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR

September 3, 2025

Lu Wang이 [arXiv]에 게시한 ‘Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

August 21, 2025

Yu Lu이 [arXiv]에 게시한 ‘DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information

August 19, 2025

Xi Yang이 [arXiv]에 게시한 ‘Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models

August 14, 2025

Guiyang Hou이 [arXiv]에 게시한 ‘Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

August 8, 2025

Xinyu Ye이 [arXiv]에 게시한 ‘On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fine-tuning

[논문리뷰] Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR

September 24, 2025

Zeina Aldallal이 [arXiv]에 게시한 ‘Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents

September 22, 2025

Chao Zhang이 [arXiv]에 게시한 ‘Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks

September 19, 2025

Xijun Gu이 [arXiv]에 게시한 ‘MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning

August 29, 2025

Simin Ma이 [arXiv]에 게시한 ‘TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Unraveling the cognitive patterns of Large Language Models through module communities

August 27, 2025

Jianxi Gao이 [arXiv]에 게시한 ‘Unraveling the cognitive patterns of Large Language Models through module communities’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning

August 27, 2025

Arman Cohan이 [arXiv]에 게시한 ‘Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning

August 25, 2025

Yulun Zhang이 [arXiv]에 게시한 ‘CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning’ 논문에 대한 자세한 리뷰...

[논문리뷰] AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance

August 14, 2025

Yong Li이 [arXiv]에 게시한 ‘AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] BiasGym: Fantastic Biases and How to Find (and Remove) Them

August 13, 2025

Arnav Arora이 [arXiv]에 게시한 ‘BiasGym: Fantastic Biases and How to Find (and Remove) Them’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal

August 11, 2025

Chengcheng Wan이 [arXiv]에 게시한 ‘Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Supervised Learning

[논문리뷰] Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation

September 19, 2025

Xihui Liu이 [arXiv]에 게시한 ‘Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Does DINOv3 Set a New Medical Vision Standard?

September 9, 2025

Bailiang Jian이 [arXiv]에 게시한 ‘Does DINOv3 Set a New Medical Vision Standard?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views

September 3, 2025

Junchi Yan이 [arXiv]에 게시한 ‘Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Vie...

[논문리뷰] M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision

September 3, 2025

Yan-Jie Zhou이 [arXiv]에 게시한 ‘M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mobile-Agent-v3: Foundamental Agents for GUI Automation

August 22, 2025

Haowei Liu이 [arXiv]에 게시한 ‘Mobile-Agent-v3: Foundamental Agents for GUI Automation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

August 21, 2025

Yu Lu이 [arXiv]에 게시한 ‘DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Representing Speech Through Autoregressive Prediction of Cochlear Tokens

August 19, 2025

Daniel L. K. Yamins이 [arXiv]에 게시한 ‘Representing Speech Through Autoregressive Prediction of Cochlear Tokens’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Test-Time Reinforcement Learning for GUI Grounding via Region Consistency

August 13, 2025

Zhengxi Lu이 [arXiv]에 게시한 ‘Test-Time Reinforcement Learning for GUI Grounding via Region Consistency’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification

August 3, 2025

Abdelmalik Taleb-Ahmed이 [arXiv]에 게시한 ‘Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification’ 논문에 대한 ...

Back to Top ↑

3D Gaussian Splatting

[논문리뷰] VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

September 24, 2025

Haoxiao Wang이 [arXiv]에 게시한 ‘VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

September 24, 2025

Yifeng Jiang이 [arXiv]에 게시한 ‘Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction

September 24, 2025

Jin Zheng이 [arXiv]에 게시한 ‘GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes

September 22, 2025

Narendra Ahuja이 [arXiv]에 게시한 ‘RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models

August 27, 2025

Beiqi Chen이 [arXiv]에 게시한 ‘ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research

August 20, 2025

Susanne Schmidt이 [arXiv]에 게시한 ‘Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

August 20, 2025

Yen-Yu Lin이 [arXiv]에 게시한 ‘LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors

August 14, 2025

Qingnan Fan이 [arXiv]에 게시한 ‘GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NeRF Is a Valuable Assistant for 3D Gaussian Splatting

August 3, 2025

ZeSheng Wang이 [arXiv]에 게시한 ‘NeRF Is a Valuable Assistant for 3D Gaussian Splatting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Augmentation

[논문리뷰] Synthetic bootstrapped pretraining

September 23, 2025

Emmanuel Candès이 [arXiv]에 게시한 ‘Synthetic bootstrapped pretraining’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

September 23, 2025

Pengze Zhang이 [arXiv]에 게시한 ‘OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search

September 10, 2025

Tianjian Li이 [arXiv]에 게시한 ‘Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem

September 9, 2025

Damien Sileo이 [arXiv]에 게시한 ‘Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms

August 15, 2025

Ziyin Zhang이 [arXiv]에 게시한 ‘From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms’ 논문에 대한 자세한 ...

[논문리뷰] TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation

August 13, 2025

Rachel Bawden이 [arXiv]에 게시한 ‘TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation

August 12, 2025

Hengtao Shen이 [arXiv]에 게시한 ‘Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward

August 6, 2025

Songyang Gao이 [arXiv]에 게시한 ‘CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Phi-Ground Tech Report: Advancing Perception in GUI Grounding

August 3, 2025

Kai Qiu이 [arXiv]에 게시한 ‘Phi-Ground Tech Report: Advancing Perception in GUI Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Agent Systems

[논문리뷰] Virtual Agent Economies

September 15, 2025

William A. Cunningham이 [arXiv]에 게시한 ‘Virtual Agent Economies’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading

September 15, 2025

Chenyu You이 [arXiv]에 게시한 ‘QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EnvX: Agentize Everything with Agentic AI

September 11, 2025

Wenzheng Tom Tang이 [arXiv]에 게시한 ‘EnvX: Agentize Everything with Agentic AI’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers

September 9, 2025

Xia Xiao이 [arXiv]에 게시한 ‘Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications

August 25, 2025

Liuyi Yao이 [arXiv]에 게시한 ‘AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

August 20, 2025

Liam-Liu이 [arXiv]에 게시한 ‘Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks

August 12, 2025

Hongxing Li이 [arXiv]에 게시한 ‘OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

August 12, 2025

Xinhao Yi이 [arXiv]에 게시한 ‘A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems’ 논문에 대한 자세...

[논문리뷰] SWE-Exp: Experience-Driven Software Issue Resolution

August 4, 2025

Heng Lian이 [arXiv]에 게시한 ‘SWE-Exp: Experience-Driven Software Issue Resolution’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Curriculum Learning

[논문리뷰] Improving Context Fidelity via Native Retrieval-Augmented Reasoning

September 18, 2025

Xiangru Tang이 [arXiv]에 게시한 ‘Improving Context Fidelity via Native Retrieval-Augmented Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning

August 15, 2025

Xiaowan Wang이 [arXiv]에 게시한 ‘We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Train Long, Think Short: Curriculum Learning for Efficient Reasoning

August 13, 2025

Marzyeh Ghassemi이 [arXiv]에 게시한 ‘Train Long, Think Short: Curriculum Learning for Efficient Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Aryabhata: An exam-focused language model for JEE Math

August 13, 2025

Sandeep Varma이 [arXiv]에 게시한 ‘Aryabhata: An exam-focused language model for JEE Math’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] R-Zero: Self-Evolving Reasoning LLM from Zero Data

August 8, 2025

Zongxia Li이 [arXiv]에 게시한 ‘R-Zero: Self-Evolving Reasoning LLM from Zero Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience

August 7, 2025

Xiaoyi Dong이 [arXiv]에 게시한 ‘SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards

August 7, 2025

Ling-I Wu이 [arXiv]에 게시한 ‘IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Qwen-Image Technical Report

August 5, 2025

Kaiyuan Gao이 [arXiv]에 게시한 ‘Qwen-Image Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models’ Instruction Following

August 5, 2025

Jiaqing Liang이 [arXiv]에 게시한 ‘Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models’ Instruction Following’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Instruction Tuning

[논문리뷰] EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence

September 19, 2025

Qinghua Huang이 [arXiv]에 게시한 ‘EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale

September 18, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation

September 16, 2025

Heshaam Faili이 [arXiv]에 게시한 ‘SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Efficient Code Embeddings from Code Generation Models

September 1, 2025

Han Xiao이 [arXiv]에 게시한 ‘Efficient Code Embeddings from Code Generation Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Do What? Teaching Vision-Language-Action Models to Reject the Impossible

August 25, 2025

Roei Herzig이 [arXiv]에 게시한 ‘Do What? Teaching Vision-Language-Action Models to Reject the Impossible’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models

August 14, 2025

Dongdong Zhang이 [arXiv]에 게시한 ‘VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction

August 8, 2025

Prajit Das이 [arXiv]에 게시한 ‘PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report

August 5, 2025

Anu Vellore이 [arXiv]에 게시한 ‘Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation

August 5, 2025

Yang Tian이 [arXiv]에 게시한 ‘InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image Editing

[논문리뷰] Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation

September 24, 2025

Jianbin Zheng이 [arXiv]에 게시한 ‘Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence

September 16, 2025

Lionel M. Ni이 [arXiv]에 게시한 ‘LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reconstruction Alignment Improves Unified Multimodal Models

September 10, 2025

XuDong Wang이 [arXiv]에 게시한 ‘Reconstruction Alignment Improves Unified Multimodal Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From Editor to Dense Geometry Estimator

September 5, 2025

Lang Nie이 [arXiv]에 게시한 ‘From Editor to Dense Geometry Estimator’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing

September 3, 2025

Amin Heyrani Nobar이 [arXiv]에 게시한 ‘Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

August 15, 2025

Quan Sun이 [arXiv]에 게시한 ‘NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control

August 12, 2025

Hongyu Liu이 [arXiv]에 게시한 ‘Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation

August 6, 2025

Tianyidan Xie이 [arXiv]에 게시한 ‘Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Qwen-Image Technical Report

August 5, 2025

Kaiyuan Gao이 [arXiv]에 게시한 ‘Qwen-Image Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Autoregressive Models

[논문리뷰] A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning

September 22, 2025

Jiangmiao이 [arXiv]에 게시한 ‘A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation

September 19, 2025

Xihui Liu이 [arXiv]에 게시한 ‘Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing

September 3, 2025

Amin Heyrani Nobar이 [arXiv]에 게시한 ‘Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FastMesh:Efficient Artistic Mesh Generation via Component Decoupling

August 27, 2025

Xingang Pan이 [arXiv]에 게시한 ‘FastMesh:Efficient Artistic Mesh Generation via Component Decoupling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SpotEdit: Evaluating Visually-Guided Image Editing Methods

August 26, 2025

Ersin Yumer이 [arXiv]에 게시한 ‘SpotEdit: Evaluating Visually-Guided Image Editing Methods’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Representing Speech Through Autoregressive Prediction of Cochlear Tokens

August 19, 2025

Daniel L. K. Yamins이 [arXiv]에 게시한 ‘Representing Speech Through Autoregressive Prediction of Cochlear Tokens’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

August 15, 2025

Quan Sun이 [arXiv]에 게시한 ‘NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VertexRegen: Mesh Generation with Continuous Level of Detail

August 13, 2025

Jakob Engel이 [arXiv]에 게시한 ‘VertexRegen: Mesh Generation with Continuous Level of Detail’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation

August 6, 2025

Tianyidan Xie이 [arXiv]에 게시한 ‘Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vision-Language Models (VLMs)

[논문리뷰] OpenGVL - Benchmarking Visual Temporal Progress for Data Curation

September 24, 2025

Viktor Petrenko이 [arXiv]에 게시한 ‘OpenGVL - Benchmarking Visual Temporal Progress for Data Curation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual Programmability: A Guide for Code-as-Thought in Chart Understanding

September 12, 2025

Ethan Chern이 [arXiv]에 게시한 ‘Visual Programmability: A Guide for Code-as-Thought in Chart Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Focusing by Contrastive Attention: Enhancing VLMs’ Visual Reasoning

September 9, 2025

Baolong Bi이 [arXiv]에 게시한 ‘Focusing by Contrastive Attention: Enhancing VLMs’ Visual Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning

September 9, 2025

Dhanvin Sanjay Namboodiri이 [arXiv]에 게시한 ‘D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Robix: A Unified Model for Robot Interaction, Reasoning and Planning

September 4, 2025

Zixuan Wang이 [arXiv]에 게시한 ‘Robix: A Unified Model for Robot Interaction, Reasoning and Planning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

September 3, 2025

Jianwei Yang이 [arXiv]에 게시한 ‘LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding

August 14, 2025

Di Zhang이 [arXiv]에 게시한 ‘IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Adapting Vision-Language Models Without Labels: A Comprehensive Survey

August 11, 2025

Eleni Chatzi이 [arXiv]에 게시한 ‘Adapting Vision-Language Models Without Labels: A Comprehensive Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HPSv3: Towards Wide-Spectrum Human Preference Score

August 7, 2025

Hongsheng Li이 [arXiv]에 게시한 ‘HPSv3: Towards Wide-Spectrum Human Preference Score’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Supervised Fine-Tuning

[논문리뷰] VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery

September 23, 2025

Shiya Huang이 [arXiv]에 게시한 ‘VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research

September 17, 2025

Houquan Zhou이 [arXiv]에 게시한 ‘WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning

September 17, 2025

Huifeng Yin이 [arXiv]에 게시한 ‘WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation

September 16, 2025

Heshaam Faili이 [arXiv]에 게시한 ‘SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?

September 5, 2025

Yu Fu이 [arXiv]에 게시한 ‘Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

August 21, 2025

Guoyin Wang이 [arXiv]에 게시한 ‘On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting’ 논문에 대한...

[논문리뷰] Thyme: Think Beyond Images

August 18, 2025

Wei Chen이 [arXiv]에 게시한 ‘Thyme: Think Beyond Images’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Aryabhata: An exam-focused language model for JEE Math

August 13, 2025

Sandeep Varma이 [arXiv]에 게시한 ‘Aryabhata: An exam-focused language model for JEE Math’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks

August 7, 2025

Haozhe Zhang이 [arXiv]에 게시한 ‘Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Generation

[논문리뷰] OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

September 23, 2025

Pengze Zhang이 [arXiv]에 게시한 ‘OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

September 16, 2025

Yang Zhou이 [arXiv]에 게시한 ‘OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 3D and 4D World Modeling: A Survey

September 11, 2025

Ao Liang이 [arXiv]에 게시한 ‘3D and 4D World Modeling: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CineScale: Free Lunch in High-Resolution Cinematic Visual Generation

August 27, 2025

Ziwei Liu이 [arXiv]에 게시한 ‘CineScale: Free Lunch in High-Resolution Cinematic Visual Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Waver: Wave Your Way to Lifelike Video Generation

August 22, 2025

Yifu Zhang이 [arXiv]에 게시한 ‘Waver: Wave Your Way to Lifelike Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation

August 14, 2025

Chen Li이 [arXiv]에 게시한 ‘Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Cut2Next: Generating Next Shot via In-Context Tuning

August 13, 2025

Yu Qiao이 [arXiv]에 게시한 ‘Cut2Next: Generating Next Shot via In-Context Tuning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation

August 12, 2025

Xiaokun Feng이 [arXiv]에 게시한 ‘Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation

August 8, 2025

Shengcong Chen이 [arXiv]에 게시한 ‘Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Diffusion Model

[논문리뷰] C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection

September 3, 2025

Vito Renó이 [arXiv]에 게시한 ‘C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling

August 26, 2025

Jiaqi Li이 [arXiv]에 게시한 ‘TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding

August 22, 2025

Rui Guo이 [arXiv]에 게시한 ‘When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Waver: Wave Your Way to Lifelike Video Generation

August 22, 2025

Yifu Zhang이 [arXiv]에 게시한 ‘Waver: Wave Your Way to Lifelike Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniTry: Virtual Try-On Anything without Masks

August 20, 2025

Xiaoduan Feng이 [arXiv]에 게시한 ‘OmniTry: Virtual Try-On Anything without Masks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation

August 18, 2025

Junyong Noh이 [arXiv]에 게시한 ‘StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors

August 14, 2025

Qingnan Fan이 [arXiv]에 게시한 ‘GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents

August 12, 2025

Mohit Bansal이 [arXiv]에 게시한 ‘Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation

August 8, 2025

Shengcong Chen이 [arXiv]에 게시한 ‘Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gaussian Splatting

[논문리뷰] SPATIALGEN: Layout-guided 3D Indoor Scene Generation

September 22, 2025

Yongsen Mao이 [arXiv]에 게시한 ‘SPATIALGEN: Layout-guided 3D Indoor Scene Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting

August 26, 2025

Yanzhe Liang이 [arXiv]에 게시한 ‘MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds

August 22, 2025

Chuiyun Wu이 [arXiv]에 게시한 ‘Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Tinker: Diffusion’s Gift to 3D–Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization

August 21, 2025

Hao Chen이 [arXiv]에 게시한 ‘Tinker: Diffusion’s Gift to 3D–Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Matrix-3D: Omnidirectional Explorable 3D World Generation

August 13, 2025

Yuqi Li이 [arXiv]에 게시한 ‘Matrix-3D: Omnidirectional Explorable 3D World Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CharacterShot: Controllable and Consistent 4D Character Animation

August 13, 2025

Fei Shen이 [arXiv]에 게시한 ‘CharacterShot: Controllable and Consistent 4D Character Animation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

August 7, 2025

Feng Zhao이 [arXiv]에 게시한 ‘Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] iLRM: An Iterative Large 3D Reconstruction Model

August 3, 2025

Abdelrahman Mohamed이 [arXiv]에 게시한 ‘iLRM: An Iterative Large 3D Reconstruction Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Learning

[논문리뷰] VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

September 12, 2025

Zirui Ge이 [arXiv]에 게시한 ‘VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Interleaving Reasoning for Better Text-to-Image Generation

September 9, 2025

Shixiang Tang이 [arXiv]에 게시한 ‘Interleaving Reasoning for Better Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning

September 3, 2025

Zirui Wang이 [arXiv]에 게시한 ‘OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Improving Large Vision and Language Models by Learning from a Panel of Peers

September 3, 2025

Simon Jenni이 [arXiv]에 게시한 ‘Improving Large Vision and Language Models by Learning from a Panel of Peers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping

August 19, 2025

Tyler Derr이 [arXiv]에 게시한 ‘Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

August 15, 2025

Quan Sun이 [arXiv]에 게시한 ‘NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Adapting Vision-Language Models Without Labels: A Comprehensive Survey

August 11, 2025

Eleni Chatzi이 [arXiv]에 게시한 ‘Adapting Vision-Language Models Without Labels: A Comprehensive Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Multimodal Referring Segmentation: A Survey

August 4, 2025

Zuxuan Wu이 [arXiv]에 게시한 ‘Multimodal Referring Segmentation: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reward Modeling

[논문리뷰] Reinforcement Learning on Pre-Training Data

September 24, 2025

Evander Yang이 [arXiv]에 게시한 ‘Reinforcement Learning on Pre-Training Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning

September 22, 2025

Jiangmiao이 [arXiv]에 게시한 ‘A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Language Self-Play For Data-Free Training

September 10, 2025

Vijai Mohan이 [arXiv]에 게시한 ‘Language Self-Play For Data-Free Training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Improving Large Vision and Language Models by Learning from a Panel of Peers

September 3, 2025

Simon Jenni이 [arXiv]에 게시한 ‘Improving Large Vision and Language Models by Learning from a Panel of Peers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SSRL: Self-Search Reinforcement Learning

August 18, 2025

Yanxu Chen이 [arXiv]에 게시한 ‘SSRL: Self-Search Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

August 18, 2025

Mu Xu이 [arXiv]에 게시한 ‘FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforcement Learning in Vision: A Survey

August 12, 2025

Qingwei Meng이 [arXiv]에 게시한 ‘Reinforcement Learning in Vision: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models’ Instruction Following

August 5, 2025

Jiaqing Liang이 [arXiv]에 게시한 ‘Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models’ Instruction Following’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Language Models

[논문리뷰] Causal Attention with Lookahead Keys

September 10, 2025

Quanquan Gu이 [arXiv]에 게시한 ‘Causal Attention with Lookahead Keys’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Why Language Models Hallucinate

September 8, 2025

Edwin Zhang이 [arXiv]에 게시한 ‘Why Language Models Hallucinate’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations

September 4, 2025

Yoav Gur-Arieh이 [arXiv]에 게시한 ‘LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Jointly Reinforcing Diversity and Quality in Language Model Generations

September 3, 2025

Tianlu이 [arXiv]에 게시한 ‘Jointly Reinforcing Diversity and Quality in Language Model Generations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models

August 20, 2025

Zishang Jiang이 [arXiv]에 게시한 ‘A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences

August 12, 2025

Matvey Skripkin이 [arXiv]에 게시한 ‘Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

August 6, 2025

Fan Xia이 [arXiv]에 게시한 ‘Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction

August 6, 2025

Jui-Hui Chung이 [arXiv]에 게시한 ‘Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Alignment

[논문리뷰] SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

September 18, 2025

Zhun Wang이 [arXiv]에 게시한 ‘SteeringControl: Holistic Evaluation of Alignment Steering in LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting

September 16, 2025

Changlong Yu이 [arXiv]에 게시한 ‘Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IntrEx: A Dataset for Modeling Engagement in Educational Conversations

September 15, 2025

Gabriele Pergola이 [arXiv]에 게시한 ‘IntrEx: A Dataset for Modeling Engagement in Educational Conversations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

August 21, 2025

Guoyin Wang이 [arXiv]에 게시한 ‘On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting’ 논문에 대한...

[논문리뷰] Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment

August 14, 2025

Lei Fan이 [arXiv]에 게시한 ‘Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future

August 12, 2025

Qiufeng Wang이 [arXiv]에 게시한 ‘Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities

August 8, 2025

Zhijie Sang이 [arXiv]에 게시한 ‘InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TRACEALIGN – Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs

August 6, 2025

Aman Chadha이 [arXiv]에 게시한 ‘TRACEALIGN – Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Prompt Engineering

[논문리뷰] Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications

September 24, 2025

Genady Beryozkin이 [arXiv]에 게시한 ‘Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications’ 논문에 ...

[논문리뷰] Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration

September 19, 2025

Zhilin Wang이 [arXiv]에 게시한 ‘Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CLIPSym: Delving into Symmetry Detection with CLIP

September 1, 2025

Raymond A. Yeh이 [arXiv]에 게시한 ‘CLIPSym: Delving into Symmetry Detection with CLIP’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Prompt Orchestration Markup Language

August 20, 2025

Yuqing Yang이 [arXiv]에 게시한 ‘Prompt Orchestration Markup Language’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Leveraging Large Language Models for Predictive Analysis of Human Misery

August 20, 2025

Abhilash Nandy이 [arXiv]에 게시한 ‘Leveraging Large Language Models for Predictive Analysis of Human Misery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy

August 13, 2025

Elizabeth Karpinski이 [arXiv]에 게시한 ‘Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

August 12, 2025

Xinhao Yi이 [arXiv]에 게시한 ‘A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems’ 논문에 대한 자세...

[논문리뷰] Sel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generation

August 7, 2025

Hao Huang이 [arXiv]에 게시한 ‘Sel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Synthetic Data

[논문리뷰] Synthetic bootstrapped pretraining

September 23, 2025

Emmanuel Candès이 [arXiv]에 게시한 ‘Synthetic bootstrapped pretraining’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning

September 17, 2025

Huifeng Yin이 [arXiv]에 게시한 ‘WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] So let's replace this phrase with insult... Lessons learned from generation of toxic texts with LLMs

September 11, 2025

Alexander Panchenko이 [arXiv]에 게시한 ‘ So let's replace this phrase with insult... Lessons learned from generation of toxic texts with LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reverse-Engineered Reasoning for Open-Ended Generation

September 9, 2025

Wangchunshu Zhou이 [arXiv]에 게시한 ‘Reverse-Engineered Reasoning for Open-Ended Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LuxDiT: Lighting Estimation with Video Diffusion Transformer

September 8, 2025

Sanja Fidler이 [arXiv]에 게시한 ‘LuxDiT: Lighting Estimation with Video Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ROSE: Remove Objects with Side Effects in Videos

August 29, 2025

Hantang Liu이 [arXiv]에 게시한 ‘ROSE: Remove Objects with Side Effects in Videos’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation

August 14, 2025

Zhenghao Hu이 [arXiv]에 게시한 ‘Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Evaluating, Synthesizing, and Enhancing for Customer Support Conversation

August 8, 2025

Feng Chen이 [arXiv]에 게시한 ‘Evaluating, Synthesizing, and Enhancing for Customer Support Conversation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Question Answering

[논문리뷰] VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery

September 23, 2025

Shiya Huang이 [arXiv]에 게시한 ‘VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

September 22, 2025

jialingt이 [arXiv]에 게시한 ‘MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook

September 18, 2025

Bowen Zhou이 [arXiv]에 게시한 ‘MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GenExam: A Multidisciplinary Text-to-Image Exam

September 18, 2025

Yu Qiao이 [arXiv]에 게시한 ‘GenExam: A Multidisciplinary Text-to-Image Exam’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge

September 17, 2025

Wentao Zhang이 [arXiv]에 게시한 ‘Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Measuring Epistemic Humility in Multimodal Large Language Models

September 16, 2025

Kaiyang Zhou이 [arXiv]에 게시한 ‘Measuring Epistemic Humility in Multimodal Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning

September 8, 2025

Amit Namburi이 [arXiv]에 게시한 ‘WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling

August 8, 2025

Ruolin Shen이 [arXiv]에 게시한 ‘Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling’ 논문에 대한 자세한 리뷰입...

Back to Top ↑

Multimodal Large Language Models

[논문리뷰] VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery

September 23, 2025

Shiya Huang이 [arXiv]에 게시한 ‘VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent

September 22, 2025

Jiahui Yang이 [arXiv]에 게시한 ‘BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding

September 19, 2025

Rynson W. H. Lau이 [arXiv]에 게시한 ‘Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Measuring Epistemic Humility in Multimodal Large Language Models

September 16, 2025

Kaiyang Zhou이 [arXiv]에 게시한 ‘Measuring Epistemic Humility in Multimodal Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning

September 8, 2025

Amit Namburi이 [arXiv]에 게시한 ‘WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

August 26, 2025

jinglinglin이 [arXiv]에 게시한 ‘InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations

August 20, 2025

Mounia Lalmas이 [arXiv]에 게시한 ‘Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs

August 11, 2025

Guohang Yan이 [arXiv]에 게시한 ‘MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GRPO

[논문리뷰] MAPO: Mixed Advantage Policy Optimization

September 24, 2025

Xuankun Rong이 [arXiv]에 게시한 ‘MAPO: Mixed Advantage Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation

September 19, 2025

Kishan Panaganti이 [arXiv]에 게시한 ‘Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Inpainting-Guided Policy Optimization for Diffusion Large Language Models

September 15, 2025

Chenyu Wang이 [arXiv]에 게시한 ‘Inpainting-Guided Policy Optimization for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforced Visual Perception with Tools

September 9, 2025

Mingyang Fu이 [arXiv]에 게시한 ‘Reinforced Visual Perception with Tools’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

August 29, 2025

Jiazi Bu이 [arXiv]에 게시한 ‘Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TempFlow-GRPO: When Timing Matters for GRPO in Flow Models

August 20, 2025

Jian Yang이 [arXiv]에 게시한 ‘TempFlow-GRPO: When Timing Matters for GRPO in Flow Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UI-Venus Technical Report: Building High-performance UI Agents with RFT

August 15, 2025

Shuheng Shen이 [arXiv]에 게시한 ‘UI-Venus Technical Report: Building High-performance UI Agents with RFT’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Compressing Chain-of-Thought in LLMs via Step Entropy

August 12, 2025

Zhijian Xu이 [arXiv]에 게시한 ‘Compressing Chain-of-Thought in LLMs via Step Entropy’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Evaluation Metrics

[논문리뷰] Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems

September 22, 2025

Hung-yi Lee이 [arXiv]에 게시한 ‘Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems’ 논문에 대...

[논문리뷰] SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge

September 10, 2025

Dipanjan Das이 [arXiv]에 게시한 ‘SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Why Language Models Hallucinate

September 8, 2025

Edwin Zhang이 [arXiv]에 게시한 ‘Why Language Models Hallucinate’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables

September 2, 2025

Yu Zhao이 [arXiv]에 게시한 ‘T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SpotEdit: Evaluating Visually-Guided Image Editing Methods

August 26, 2025

Ersin Yumer이 [arXiv]에 게시한 ‘SpotEdit: Evaluating Visually-Guided Image Editing Methods’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] INTIMA: A Benchmark for Human-AI Companionship Behavior

August 22, 2025

Yacine Jernite이 [arXiv]에 게시한 ‘INTIMA: A Benchmark for Human-AI Companionship Behavior’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Advances in Speech Separation: Techniques, Challenges, and Future Trends

August 20, 2025

Zhuo Chen이 [arXiv]에 게시한 ‘Advances in Speech Separation: Techniques, Challenges, and Future Trends’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WideSearch: Benchmarking Agentic Broad Info-Seeking

August 12, 2025

Yan Gao이 [arXiv]에 게시한 ‘WideSearch: Benchmarking Agentic Broad Info-Seeking’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-supervised Learning

[논문리뷰] Reinforcement Learning on Pre-Training Data

September 24, 2025

Evander Yang이 [arXiv]에 게시한 ‘Reinforcement Learning on Pre-Training Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Understanding Embedding Scaling in Collaborative Filtering

September 23, 2025

Yonghui Yang이 [arXiv]에 게시한 ‘Understanding Embedding Scaling in Collaborative Filtering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reconstruction Alignment Improves Unified Multimodal Models

September 10, 2025

XuDong Wang이 [arXiv]에 게시한 ‘Reconstruction Alignment Improves Unified Multimodal Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Curia: A Multi-Modal Foundation Model for Radiology

September 10, 2025

Elodie Ferreres이 [arXiv]에 게시한 ‘Curia: A Multi-Modal Foundation Model for Radiology’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MedDINOv3: How to adapt vision foundation models for medical image segmentation?

September 3, 2025

Xiaofeng Yang이 [arXiv]에 게시한 ‘MedDINOv3: How to adapt vision foundation models for medical image segmentation?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment

August 28, 2025

An-An Liu이 [arXiv]에 게시한 ‘MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data

August 18, 2025

Nicolas Gonthier이 [arXiv]에 게시한 ‘MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DINOv3

August 18, 2025

Maxime Oquab이 [arXiv]에 게시한 ‘DINOv3’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hallucination

[논문리뷰] FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions

September 23, 2025

tengdai722이 [arXiv]에 게시한 ‘FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questio...

[논문리뷰] Improving Context Fidelity via Native Retrieval-Augmented Reasoning

September 18, 2025

Xiangru Tang이 [arXiv]에 게시한 ‘Improving Context Fidelity via Native Retrieval-Augmented Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Measuring Epistemic Humility in Multimodal Large Language Models

September 16, 2025

Kaiyang Zhou이 [arXiv]에 게시한 ‘Measuring Epistemic Humility in Multimodal Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Why Language Models Hallucinate

September 8, 2025

Edwin Zhang이 [arXiv]에 게시한 ‘Why Language Models Hallucinate’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding

September 3, 2025

Xuanyu Zheng이 [arXiv]에 게시한 ‘ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks

August 27, 2025

Kai Jia이 [arXiv]에 게시한 ‘ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SpotEdit: Evaluating Visually-Guided Image Editing Methods

August 26, 2025

Ersin Yumer이 [arXiv]에 게시한 ‘SpotEdit: Evaluating Visually-Guided Image Editing Methods’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information

August 19, 2025

Xi Yang이 [arXiv]에 게시한 ‘Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Question Answering

[논문리뷰] Improving Context Fidelity via Native Retrieval-Augmented Reasoning

September 18, 2025

Xiangru Tang이 [arXiv]에 게시한 ‘Improving Context Fidelity via Native Retrieval-Augmented Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge

September 10, 2025

Dipanjan Das이 [arXiv]에 게시한 ‘SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On Robustness and Reliability of Benchmark-Based Evaluation of LLMs

September 8, 2025

Kevin Roitero이 [arXiv]에 게시한 ‘On Robustness and Reliability of Benchmark-Based Evaluation of LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding

September 5, 2025

Lionel Ni이 [arXiv]에 게시한 ‘Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Open Data Synthesis For Deep Research

September 4, 2025

Zheng Liu이 [arXiv]에 게시한 ‘Open Data Synthesis For Deep Research’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ST-Raptor: LLM-Powered Semi-Structured Table Question Answering

August 26, 2025

Wei Zhou이 [arXiv]에 게시한 ‘ST-Raptor: LLM-Powered Semi-Structured Table Question Answering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Enhanced Arabic Text Retrieval with Attentive Relevance Scoring

August 3, 2025

Abdenour Hadid이 [arXiv]에 게시한 ‘Enhanced Arabic Text Retrieval with Attentive Relevance Scoring’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

MLLMs

[논문리뷰] Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding

September 5, 2025

Lionel Ni이 [arXiv]에 게시한 ‘Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From reactive to cognitive: brain-inspired spatial intelligence for embodied agents

September 2, 2025

Songming Liu이 [arXiv]에 게시한 ‘From reactive to cognitive: brain-inspired spatial intelligence for embodied agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning

August 15, 2025

Xiaowan Wang이 [arXiv]에 게시한 ‘We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

August 12, 2025

Tong Yu이 [arXiv]에 게시한 ‘VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding

August 11, 2025

Bingqi Chen이 [arXiv]에 게시한 ‘UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization

August 11, 2025

Pengxiang Li이 [arXiv]에 게시한 ‘InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs

August 3, 2025

Jiasheng Tang이 [arXiv]에 게시한 ‘TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Software Engineering

[논문리뷰] SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

September 23, 2025

Yannis Yiming He이 [arXiv]에 게시한 ‘SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects

September 23, 2025

Hang Yu이 [arXiv]에 게시한 ‘CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation

September 22, 2025

Steven Liu이 [arXiv]에 게시한 ‘RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering

September 12, 2025

Jianguo Zhang이 [arXiv]에 게시한 ‘LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning

August 7, 2025

Maksim Nekrashevich이 [arXiv]에 게시한 ‘Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Tool-integrated Reinforcement Learning for Repo Deep Search

August 6, 2025

Yanzhen Zou이 [arXiv]에 게시한 ‘Tool-integrated Reinforcement Learning for Repo Deep Search’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution

August 4, 2025

Heng Lian이 [arXiv]에 게시한 ‘SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Reasoning

[논문리뷰] MAPO: Mixed Advantage Policy Optimization

September 24, 2025

Xuankun Rong이 [arXiv]에 게시한 ‘MAPO: Mixed Advantage Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?

September 23, 2025

Jaeho Lee이 [arXiv]에 게시한 ‘AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook

September 18, 2025

Bowen Zhou이 [arXiv]에 게시한 ‘MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge

September 17, 2025

Wentao Zhang이 [arXiv]에 게시한 ‘Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning

September 9, 2025

Dhanvin Sanjay Namboodiri이 [arXiv]에 게시한 ‘D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

September 3, 2025

Jianwei Yang이 [arXiv]에 게시한 ‘LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation

August 5, 2025

Yang Tian이 [arXiv]에 게시한 ‘InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-to-Image

[논문리뷰] Can Understanding and Generation Truly Benefit Together – or Just Coexist?

September 12, 2025

Hui Han이 [arXiv]에 게시한 ‘Can Understanding and Generation Truly Benefit Together – or Just Coexist?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RewardDance: Reward Scaling in Visual Generation

September 11, 2025

Liang Li이 [arXiv]에 게시한 ‘RewardDance: Reward Scaling in Visual Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing

September 3, 2025

Amin Heyrani Nobar이 [arXiv]에 게시한 ‘Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TempFlow-GRPO: When Timing Matters for GRPO in Flow Models

August 20, 2025

Jian Yang이 [arXiv]에 게시한 ‘TempFlow-GRPO: When Timing Matters for GRPO in Flow Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models

August 19, 2025

Meiqi Wu이 [arXiv]에 게시한 ‘S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Story2Board: A Training-Free Approach for Expressive Storyboard Generation

August 14, 2025

Dani Lischinski이 [arXiv]에 게시한 ‘Story2Board: A Training-Free Approach for Expressive Storyboard Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Qwen-Image Technical Report

August 5, 2025

Kaiyuan Gao이 [arXiv]에 게시한 ‘Qwen-Image Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Synthesis

[논문리뷰] WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents

September 17, 2025

Wenbiao Yin이 [arXiv]에 게시한 ‘WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Scaling Agents via Continual Pre-training

September 17, 2025

Guangyu Li이 [arXiv]에 게시한 ‘Scaling Agents via Continual Pre-training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Open Data Synthesis For Deep Research

September 4, 2025

Zheng Liu이 [arXiv]에 게시한 ‘Open Data Synthesis For Deep Research’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning

August 21, 2025

anoperson이 [arXiv]에 게시한 ‘mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL

August 13, 2025

Chuyi He이 [arXiv]에 게시한 ‘Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability

August 12, 2025

Yuchen Li이 [arXiv]에 게시한 ‘ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction

August 6, 2025

Jui-Hui Chung이 [arXiv]에 게시한 ‘Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Explainable AI

[논문리뷰] Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models

September 1, 2025

Yifan Lu이 [arXiv]에 게시한 ‘Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] X-Node: Self-Explanation is All We Need

August 18, 2025

Islem Rekik이 [arXiv]에 게시한 ‘X-Node: Self-Explanation is All We Need’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms

August 15, 2025

Ziyin Zhang이 [arXiv]에 게시한 ‘From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms’ 논문에 대한 자세한 ...

[논문리뷰] Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery

August 14, 2025

Di Zhang이 [arXiv]에 게시한 ‘Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MolmoAct: Action Reasoning Models that can Reason in Space

August 12, 2025

Shuo Liu이 [arXiv]에 게시한 ‘MolmoAct: Action Reasoning Models that can Reason in Space’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models

August 7, 2025

Elisabetta Rocchetti이 [arXiv]에 게시한 ‘The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TRACEALIGN – Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs

August 6, 2025

Aman Chadha이 [arXiv]에 게시한 ‘TRACEALIGN – Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AI Agents

[논문리뷰] SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

September 23, 2025

Yannis Yiming He이 [arXiv]에 게시한 ‘SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Virtual Agent Economies

September 15, 2025

William A. Cunningham이 [arXiv]에 게시한 ‘Virtual Agent Economies’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents

September 9, 2025

James Zou이 [arXiv]에 게시한 ‘Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists

August 22, 2025

Heng Zhang이 [arXiv]에 게시한 ‘aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries

August 22, 2025

huuuyeah이 [arXiv]에 게시한 ‘LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents

August 20, 2025

Jun Dong이 [arXiv]에 게시한 ‘MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Agent Lightning: Train ANY AI Agents with Reinforcement Learning

August 7, 2025

Zilong Wang이 [arXiv]에 게시한 ‘Agent Lightning: Train ANY AI Agents with Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Large Language Models (MLLMs)

[논문리뷰] GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning

September 23, 2025

Hou Pong Chan이 [arXiv]에 게시한 ‘GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook

September 18, 2025

Bowen Zhou이 [arXiv]에 게시한 ‘MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning

September 1, 2025

Han Hu이 [arXiv]에 게시한 ‘R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation

August 27, 2025

Jiaqi Yang이 [arXiv]에 게시한 ‘OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models

August 14, 2025

Zhihan Zhou이 [arXiv]에 게시한 ‘MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models’ 논문에 대한 자세한 리뷰...

[논문리뷰] Reinforcement Learning in Vision: A Survey

August 12, 2025

Qingwei Meng이 [arXiv]에 게시한 ‘Reinforcement Learning in Vision: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LaTCoder: Converting Webpage Design to Code with Layout-as-Thought

August 7, 2025

Tianpeng Lv이 [arXiv]에 게시한 ‘LaTCoder: Converting Webpage Design to Code with Layout-as-Thought’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Supervised Fine-tuning

[논문리뷰] Mano Report

September 23, 2025

Minghui Wu이 [arXiv]에 게시한 ‘Mano Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SAIL-VL2 Technical Report

September 18, 2025

Zijian Kang이 [arXiv]에 게시한 ‘SAIL-VL2 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Towards General Agentic Intelligence via Environment Scaling

September 17, 2025

Guangyu Li이 [arXiv]에 게시한 ‘Towards General Agentic Intelligence via Environment Scaling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models

August 27, 2025

Jiangjie Chen이 [arXiv]에 게시한 ‘ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery

August 14, 2025

Di Zhang이 [arXiv]에 게시한 ‘Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization

August 12, 2025

Guanting Dong이 [arXiv]에 게시한 ‘Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following

August 7, 2025

Liang Xu이 [arXiv]에 게시한 ‘Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dataset Creation

[논문리뷰] DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultural Text Adaptation in Indian Context

September 23, 2025

Maunendra Sankar Desarkar이 [arXiv]에 게시한 ‘DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultur...

[논문리뷰] Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents

September 22, 2025

Chao Zhang이 [arXiv]에 게시한 ‘Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation

September 16, 2025

Heshaam Faili이 [arXiv]에 게시한 ‘SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MovieCORE: COgnitive REasoning in Movies

August 27, 2025

Hung-Ting Su이 [arXiv]에 게시한 ‘MovieCORE: COgnitive REasoning in Movies’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences

August 12, 2025

Matvey Skripkin이 [arXiv]에 게시한 ‘Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs

August 11, 2025

Guohang Yan이 [arXiv]에 게시한 ‘MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering

August 7, 2025

Ambuj Mehrish이 [arXiv]에 게시한 ‘SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Diffusion Transformer

[논문리뷰] Lynx: Towards High-Fidelity Personalized Video Generation

September 22, 2025

Linjie Luo이 [arXiv]에 게시한 ‘Lynx: Towards High-Fidelity Personalized Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From Editor to Dense Geometry Estimator

September 5, 2025

Lang Nie이 [arXiv]에 게시한 ‘From Editor to Dense Geometry Estimator’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation

September 4, 2025

Kai Li이 [arXiv]에 게시한 ‘Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GenCompositor: Generative Video Compositing with Diffusion Transformer

September 3, 2025

Lingen Li이 [arXiv]에 게시한 ‘GenCompositor: Generative Video Compositing with Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ROSE: Remove Objects with Side Effects in Videos

August 29, 2025

Hantang Liu이 [arXiv]에 게시한 ‘ROSE: Remove Objects with Side Effects in Videos’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Cut2Next: Generating Next Shot via In-Context Tuning

August 13, 2025

Yu Qiao이 [arXiv]에 게시한 ‘Cut2Next: Generating Next Shot via In-Context Tuning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off

August 11, 2025

jgkwak이 [arXiv]에 게시한 ‘Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Natural Language Processing

[논문리뷰] ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation

August 27, 2025

Kun Kuang이 [arXiv]에 게시한 ‘ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge

August 20, 2025

Alice Wang이 [arXiv]에 게시한 ‘Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations

August 20, 2025

Mounia Lalmas이 [arXiv]에 게시한 ‘Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Human Judgment: A Bayesian Evaluation of LLMs’ Moral Values Understanding

August 20, 2025

Alina Landowska이 [arXiv]에 게시한 ‘Beyond Human Judgment: A Bayesian Evaluation of LLMs’ Moral Values Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] X-Node: Self-Explanation is All We Need

August 18, 2025

Islem Rekik이 [arXiv]에 게시한 ‘X-Node: Self-Explanation is All We Need’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts

August 15, 2025

Rui Lu이 [arXiv]에 게시한 ‘PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms

August 15, 2025

Ziyin Zhang이 [arXiv]에 게시한 ‘From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms’ 논문에 대한 자세한 ...

Back to Top ↑

Scaling Laws

[논문리뷰] Reinforcement Learning on Pre-Training Data

September 24, 2025

Evander Yang이 [arXiv]에 게시한 ‘Reinforcement Learning on Pre-Training Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Scaling Agents via Continual Pre-training

September 17, 2025

Guangyu Li이 [arXiv]에 게시한 ‘Scaling Agents via Continual Pre-training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs

September 15, 2025

Jonas Geiping이 [arXiv]에 게시한 ‘The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Does DINOv3 Set a New Medical Vision Standard?

September 9, 2025

Bailiang Jian이 [arXiv]에 게시한 ‘Does DINOv3 Set a New Medical Vision Standard?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Fantastic Pretraining Optimizers and Where to Find Them

September 3, 2025

Percy Liang이 [arXiv]에 게시한 ‘Fantastic Pretraining Optimizers and Where to Find Them’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Provable Benefits of In-Tool Learning for Large Language Models

August 29, 2025

Vivien Cabannes이 [arXiv]에 게시한 ‘Provable Benefits of In-Tool Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks

August 27, 2025

Daisuke Nohara이 [arXiv]에 게시한 ‘Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Django

[Django] Makefile 사용하기

February 15, 2025

Django 프로젝트에서 Makefile을 사용하는 방법을 공유합니다.

[Django] 낙관적 락

February 14, 2025

Django에서 낙관적 락에 대해 알아보자

[Django] 비관적 락

February 14, 2025

Django에서 비관적 락에 대해 알아보자

[Django] index

February 14, 2025

Django에서 index의 사용법을 공유합니다.

[Django] prefetch_related

February 14, 2025

Django에서 prefetch_related의 사용법을 공유합니다.

[Django] DB 로그 확인하기

February 5, 2025

Django에서 ORM을 사용하여 데이터베이스에 접근하는 경우, 쿼리 로그를 확인하는 방법을 공유합니다.

Back to Top ↑

Information Retrieval

[논문리뷰] WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents

September 9, 2025

Aili Chen이 [arXiv]에 게시한 ‘WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings

September 5, 2025

Oren Glickman이 [arXiv]에 게시한 ‘NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations

September 4, 2025

Yoav Gur-Arieh이 [arXiv]에 게시한 ‘LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability

August 12, 2025

Yuchen Li이 [arXiv]에 게시한 ‘ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?

August 8, 2025

Junjie Yang이 [arXiv]에 게시한 ‘Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Enhanced Arabic Text Retrieval with Attentive Relevance Scoring

August 3, 2025

Abdenour Hadid이 [arXiv]에 게시한 ‘Enhanced Arabic Text Retrieval with Attentive Relevance Scoring’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spatial Reasoning

[논문리뷰] PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era

September 18, 2025

Zihao Dongfang이 [arXiv]에 게시한 ‘PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 3D Aware Region Prompted Vision Language Model

September 17, 2025

Xiaolong Li이 [arXiv]에 게시한 ‘3D Aware Region Prompted Vision Language Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning

September 12, 2025

Yuzheng Zhuang이 [arXiv]에 게시한 ‘OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual Representation Alignment for Multimodal Large Language Models

September 10, 2025

Heeseong Shin이 [arXiv]에 게시한 ‘Visual Representation Alignment for Multimodal Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RynnEC: Bringing MLLMs into Embodied World

August 21, 2025

jiangpinliu이 [arXiv]에 게시한 ‘RynnEC: Bringing MLLMs into Embodied World’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents

August 3, 2025

Anji Liu이 [arXiv]에 게시한 ‘Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Grounding

[논문리뷰] Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding

September 19, 2025

Rynson W. H. Lau이 [arXiv]에 게시한 ‘Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook

September 18, 2025

Bowen Zhou이 [arXiv]에 게시한 ‘MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Ovis2.5 Technical Report

August 19, 2025

Yang Li이 [arXiv]에 게시한 ‘Ovis2.5 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Controlling Multimodal LLMs via Reward-guided Decoding

August 18, 2025

Michal Drozdzal이 [arXiv]에 게시한 ‘Controlling Multimodal LLMs via Reward-guided Decoding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding

August 14, 2025

Di Zhang이 [arXiv]에 게시한 ‘IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs

August 3, 2025

Jiasheng Tang이 [arXiv]에 게시한 ‘TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scalability

[논문리뷰] Single-stream Policy Optimization

September 17, 2025

Zihan Ding이 [arXiv]에 게시한 ‘Single-stream Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AWorld: Orchestrating the Training Recipe for Agentic AI

August 29, 2025

Qintong Wu이 [arXiv]에 게시한 ‘AWorld: Orchestrating the Training Recipe for Agentic AI’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Neither Valid nor Reliable? Investigating the Use of LLMs as Judges

August 26, 2025

Golnoosh Farnadi이 [arXiv]에 게시한 ‘Neither Valid nor Reliable? Investigating the Use of LLMs as Judges’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CAMAR: Continuous Actions Multi-Agent Routing

August 20, 2025

Alexey Skrynnik이 [arXiv]에 게시한 ‘CAMAR: Continuous Actions Multi-Agent Routing’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities

August 8, 2025

Zhijie Sang이 [arXiv]에 게시한 ‘InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] iLRM: An Iterative Large 3D Reconstruction Model

August 3, 2025

Abdelrahman Mohamed이 [arXiv]에 게시한 ‘iLRM: An Iterative Large 3D Reconstruction Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Agent System

[논문리뷰] DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks

September 5, 2025

Jiaxuan Lu이 [arXiv]에 게시한 ‘DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Spacer: Towards Engineered Scientific Inspiration

August 27, 2025

zerojun48이 [arXiv]에 게시한 ‘Spacer: Towards Engineered Scientific Inspiration’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving

August 14, 2025

Jinjie Gu이 [arXiv]에 게시한 ‘AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling

August 8, 2025

Ruolin Shen이 [arXiv]에 게시한 ‘Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling’ 논문에 대한 자세한 리뷰입...

[논문리뷰] CellForge: Agentic Design of Virtual Cell Models

August 5, 2025

Daniel Shao이 [arXiv]에 게시한 ‘CellForge: Agentic Design of Virtual Cell Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution

August 4, 2025

Heng Lian이 [arXiv]에 게시한 ‘SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Large Language Model

[논문리뷰] Hunyuan-MT Technical Report

September 11, 2025

Yang Du이 [arXiv]에 게시한 ‘Hunyuan-MT Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VibeVoice Technical Report

August 27, 2025

Yaoyao Chang이 [arXiv]에 게시한 ‘VibeVoice Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

August 21, 2025

Jiangmiao이 [arXiv]에 게시한 ‘MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

August 11, 2025

GLM-4. 5 Team이 [arXiv]에 게시한 ‘GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction

August 7, 2025

Donghyeon Lee이 [arXiv]에 게시한 ‘CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report

August 5, 2025

Anu Vellore이 [arXiv]에 게시한 ‘Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Foundation Model

[논문리뷰] Curia: A Multi-Modal Foundation Model for Radiology

September 10, 2025

Elodie Ferreres이 [arXiv]에 게시한 ‘Curia: A Multi-Modal Foundation Model for Radiology’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Waver: Wave Your Way to Lifelike Video Generation

August 22, 2025

Yifu Zhang이 [arXiv]에 게시한 ‘Waver: Wave Your Way to Lifelike Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

August 11, 2025

GLM-4. 5 Team이 [arXiv]에 게시한 ‘GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation

August 8, 2025

Shengcong Chen이 [arXiv]에 게시한 ‘Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Qwen-Image Technical Report

August 5, 2025

Kaiyuan Gao이 [arXiv]에 게시한 ‘Qwen-Image Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report

August 5, 2025

Anu Vellore이 [arXiv]에 게시한 ‘Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mixture-of-Experts

[논문리뷰] Qwen3-Omni Technical Report

September 23, 2025

Lhma-aslp이 [arXiv]에 게시한 ‘Qwen3-Omni Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SAIL-VL2 Technical Report

September 18, 2025

Zijian Kang이 [arXiv]에 게시한 ‘SAIL-VL2 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Speed Always Wins: A Survey on Efficient Architectures for Large Language Models

August 19, 2025

Jusen Du이 [arXiv]에 게시한 ‘Speed Always Wins: A Survey on Efficient Architectures for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment

August 14, 2025

Lei Fan이 [arXiv]에 게시한 ‘Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

August 11, 2025

GLM-4. 5 Team이 [arXiv]에 게시한 ‘GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

August 5, 2025

Bin Jia이 [arXiv]에 게시한 ‘VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LoRA

[논문리뷰] ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models

August 27, 2025

Beiqi Chen이 [arXiv]에 게시한 ‘ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models

August 14, 2025

Zeynep Akata이 [arXiv]에 게시한 ‘Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation

August 12, 2025

Xiaokun Feng이 [arXiv]에 게시한 ‘Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets

August 7, 2025

MaziyarPanahi이 [arXiv]에 게시한 ‘OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets’ 논문에 대한 자세한 ...

[논문리뷰] DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework

August 7, 2025

Chao Liang이 [arXiv]에 게시한 ‘DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization

August 6, 2025

Aman Chadha이 [arXiv]에 게시한 ‘AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization...

Back to Top ↑

Temporal Consistency

[논문리뷰] VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models

September 23, 2025

Sunghyun Cho이 [arXiv]에 게시한 ‘VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment

September 23, 2025

Yue Ma이 [arXiv]에 게시한 ‘ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models

August 19, 2025

Zixiang Gao이 [arXiv]에 게시한 ‘Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CharacterShot: Controllable and Consistent 4D Character Animation

August 13, 2025

Fei Shen이 [arXiv]에 게시한 ‘CharacterShot: Controllable and Consistent 4D Character Animation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework

August 7, 2025

Chao Liang이 [arXiv]에 게시한 ‘DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation

August 6, 2025

Chenyang Si이 [arXiv]에 게시한 ‘LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Benchmark Dataset

[논문리뷰] EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI

September 16, 2025

UVSKKR이 [arXiv]에 게시한 ‘EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding

September 16, 2025

Li Zheng이 [arXiv]에 게시한 ‘Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Groundi...

[논문리뷰] Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth

September 5, 2025

Chi-Li Chen이 [arXiv]에 게시한 ‘Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables

September 2, 2025

Yu Zhao이 [arXiv]에 게시한 ‘T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FakeParts: a New Family of AI-Generated DeepFakes

August 29, 2025

Xi Wang이 [arXiv]에 게시한 ‘FakeParts: a New Family of AI-Generated DeepFakes’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding

August 7, 2025

Jianke Zhu이 [arXiv]에 게시한 ‘A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Domain Adaptation

[논문리뷰] WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers

September 22, 2025

Karun Kumar이 [arXiv]에 게시한 ‘WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation

September 16, 2025

Heshaam Faili이 [arXiv]에 게시한 ‘SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings

September 16, 2025

Yixuan Tang이 [arXiv]에 게시한 ‘GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Does DINOv3 Set a New Medical Vision Standard?

September 9, 2025

Bailiang Jian이 [arXiv]에 게시한 ‘Does DINOv3 Set a New Medical Vision Standard?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MedDINOv3: How to adapt vision foundation models for medical image segmentation?

September 3, 2025

Xiaofeng Yang이 [arXiv]에 게시한 ‘MedDINOv3: How to adapt vision foundation models for medical image segmentation?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets

August 7, 2025

MaziyarPanahi이 [arXiv]에 게시한 ‘OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets’ 논문에 대한 자세한 ...

Back to Top ↑

Reward Design

[논문리뷰] A Survey of Reinforcement Learning for Large Reasoning Models

September 11, 2025

Runze Liu이 [arXiv]에 게시한 ‘A Survey of Reinforcement Learning for Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

September 10, 2025

Xinyu Yang이 [arXiv]에 게시한 ‘Parallel-R1: Towards Parallel Thinking via Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforcement Learning Foundations for Deep Research Systems: A Survey

September 9, 2025

Wei Han이 [arXiv]에 게시한 ‘Reinforcement Learning Foundations for Deep Research Systems: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning

August 25, 2025

Pengcheng Qiu이 [arXiv]에 게시한 ‘End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models

August 15, 2025

Qinghao Ye이 [arXiv]에 게시한 ‘Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Sotopia-RL: Reward Design for Social Intelligence

August 7, 2025

Keyang Xuan이 [arXiv]에 게시한 ‘Sotopia-RL: Reward Design for Social Intelligence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Large Reasoning Models

[논문리뷰] What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT

September 24, 2025

Anthony Hartshorn이 [arXiv]에 게시한 ‘What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions

September 23, 2025

tengdai722이 [arXiv]에 게시한 ‘FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questio...

[논문리뷰] A Survey of Reinforcement Learning for Large Reasoning Models

September 11, 2025

Runze Liu이 [arXiv]에 게시한 ‘A Survey of Reinforcement Learning for Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches

August 13, 2025

Qiang Ju이 [arXiv]에 게시한 ‘HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal

August 11, 2025

Chengcheng Wan이 [arXiv]에 게시한 ‘Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Don’t Overthink It: A Survey of Efficient R1-style Large Reasoning Models

August 8, 2025

Fangzhou Yao이 [arXiv]에 게시한 ‘Don’t Overthink It: A Survey of Efficient R1-style Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Zero-Shot Learning

[논문리뷰] Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications

September 24, 2025

Genady Beryozkin이 [arXiv]에 게시한 ‘Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications’ 논문에 ...

[논문리뷰] Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding

September 19, 2025

Rynson W. H. Lau이 [arXiv]에 게시한 ‘Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings

September 5, 2025

Oren Glickman이 [arXiv]에 게시한 ‘NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Tinker: Diffusion’s Gift to 3D–Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization

August 21, 2025

Hao Chen이 [arXiv]에 게시한 ‘Tinker: Diffusion’s Gift to 3D–Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations

August 20, 2025

Mounia Lalmas이 [arXiv]에 게시한 ‘Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Adapting Vision-Language Models Without Labels: A Comprehensive Survey

August 11, 2025

Eleni Chatzi이 [arXiv]에 게시한 ‘Adapting Vision-Language Models Without Labels: A Comprehensive Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Evaluation

[논문리뷰] GenExam: A Multidisciplinary Text-to-Image Exam

September 18, 2025

Yu Qiao이 [arXiv]에 게시한 ‘GenExam: A Multidisciplinary Text-to-Image Exam’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?

September 5, 2025

Yu Fu이 [arXiv]에 게시한 ‘Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications

August 25, 2025

Liuyi Yao이 [arXiv]에 게시한 ‘AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries

August 22, 2025

huuuyeah이 [arXiv]에 게시한 ‘LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Survey on Large Language Model Benchmarks

August 22, 2025

Siyi Li이 [arXiv]에 게시한 ‘A Survey on Large Language Model Benchmarks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

August 12, 2025

Kai Zou이 [arXiv]에 게시한 ‘BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Reasoning

[논문리뷰] Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning

September 23, 2025

Damien Sileo이 [arXiv]에 게시한 ‘Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding

September 10, 2025

Yongcheng Zeng이 [arXiv]에 게시한 ‘Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] StepWiser: Stepwise Generative Judges for Wiser Reasoning

August 28, 2025

Olga Golovneva이 [arXiv]에 게시한 ‘StepWiser: Stepwise Generative Judges for Wiser Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning

August 25, 2025

Yulun Zhang이 [arXiv]에 게시한 ‘CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning’ 논문에 대한 자세한 리뷰...

[논문리뷰] Deep Think with Confidence

August 22, 2025

Xuewei Wang이 [arXiv]에 게시한 ‘Deep Think with Confidence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning

August 12, 2025

Jiaheng Liu이 [arXiv]에 게시한 ‘Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-agent Systems

[논문리뷰] RecoWorld: Building Simulated Environments for Agentic Recommender Systems

September 19, 2025

Mingyuan Wu이 [arXiv]에 게시한 ‘RecoWorld: Building Simulated Environments for Agentic Recommender Systems’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction

September 3, 2025

bindsch이 [arXiv]에 게시한 ‘SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists

August 22, 2025

Heng Zhang이 [arXiv]에 게시한 ‘aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery

August 21, 2025

zijieqiu이 [arXiv]에 게시한 ‘From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy

August 13, 2025

Elizabeth Karpinski이 [arXiv]에 게시한 ‘Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WideSearch: Benchmarking Agentic Broad Info-Seeking

August 12, 2025

Yan Gao이 [arXiv]에 게시한 ‘WideSearch: Benchmarking Agentic Broad Info-Seeking’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Merging

[논문리뷰] Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale

September 18, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Delta Activations: A Representation for Finetuned Large Language Models

September 5, 2025

Ser-Nam Lim이 [arXiv]에 게시한 ‘Delta Activations: A Representation for Finetuned Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic

September 3, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation

August 20, 2025

Jonas Geiping이 [arXiv]에 게시한 ‘MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models

August 14, 2025

Dongdong Zhang이 [arXiv]에 게시한 ‘VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Aryabhata: An exam-focused language model for JEE Math

August 13, 2025

Sandeep Varma이 [arXiv]에 게시한 ‘Aryabhata: An exam-focused language model for JEE Math’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Robustness

[논문리뷰] Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?

September 5, 2025

Yu Fu이 [arXiv]에 게시한 ‘Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AHELM: A Holistic Evaluation of Audio-Language Models

September 1, 2025

Siwei Yang이 [arXiv]에 게시한 ‘AHELM: A Holistic Evaluation of Audio-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD

August 29, 2025

Roy Ka-Wei Lee이 [arXiv]에 게시한 ‘Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Processing and acquisition traces in visual encoders: What does CLIP know about your camera?

August 15, 2025

Giorgos Tolias이 [arXiv]에 게시한 ‘Processing and acquisition traces in visual encoders: What does CLIP know about your camera?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models

August 14, 2025

Zhihan Zhou이 [arXiv]에 게시한 ‘MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models’ 논문에 대한 자세한 리뷰...

[논문리뷰] AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving

August 14, 2025

Jinjie Gu이 [arXiv]에 게시한 ‘AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Novel View Synthesis

[논문리뷰] VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

September 24, 2025

Haoxiao Wang이 [arXiv]에 게시한 ‘VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis

September 24, 2025

Dan Xu이 [arXiv]에 게시한 ‘HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance

September 19, 2025

Ruibo Li이 [arXiv]에 게시한 ‘WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting

August 26, 2025

Yanzhe Liang이 [arXiv]에 게시한 ‘MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

August 20, 2025

Yen-Yu Lin이 [arXiv]에 게시한 ‘LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors

August 14, 2025

Qingnan Fan이 [arXiv]에 게시한 ‘GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vision-Language Model

[논문리뷰] Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR

September 24, 2025

Zeina Aldallal이 [arXiv]에 게시한 ‘Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SAIL-VL2 Technical Report

September 18, 2025

Zijian Kang이 [arXiv]에 게시한 ‘SAIL-VL2 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark

September 12, 2025

Shuai Bai이 [arXiv]에 게시한 ‘FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting

September 8, 2025

Vanessa Wildman이 [arXiv]에 게시한 ‘MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting’ 논...

[논문리뷰] Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation

August 20, 2025

Fei Ni이 [arXiv]에 게시한 ‘Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models

August 14, 2025

Dongdong Zhang이 [arXiv]에 게시한 ‘VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Interpretability

[논문리뷰] From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models

August 21, 2025

Ziyan Kuang이 [arXiv]에 게시한 ‘From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents

August 20, 2025

Flora D. Salim이 [arXiv]에 게시한 ‘ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] X-Node: Self-Explanation is All We Need

August 18, 2025

Islem Rekik이 [arXiv]에 게시한 ‘X-Node: Self-Explanation is All We Need’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation

August 8, 2025

Jian Yang이 [arXiv]에 게시한 ‘RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Persona Vectors: Monitoring and Controlling Character Traits in Language Models

August 3, 2025

Jack Lindsey이 [arXiv]에 게시한 ‘Persona Vectors: Monitoring and Controlling Character Traits in Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Preference Optimization

[논문리뷰] OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

September 23, 2025

Pengze Zhang이 [arXiv]에 게시한 ‘OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

August 21, 2025

Yu Lu이 [arXiv]에 게시한 ‘DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Ovis2.5 Technical Report

August 19, 2025

Yang Li이 [arXiv]에 게시한 ‘Ovis2.5 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

August 18, 2025

Mu Xu이 [arXiv]에 게시한 ‘FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs

August 3, 2025

Jiasheng Tang이 [arXiv]에 게시한 ‘TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Reconstruction

[논문리뷰] MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

August 21, 2025

Jiangmiao이 [arXiv]에 게시한 ‘MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration

August 19, 2025

Evgeny Burnaev이 [arXiv]에 게시한 ‘G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer

August 15, 2025

Honghua Chen이 [arXiv]에 게시한 ‘STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Matrix-3D: Omnidirectional Explorable 3D World Generation

August 13, 2025

Yuqi Li이 [arXiv]에 게시한 ‘Matrix-3D: Omnidirectional Explorable 3D World Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] iLRM: An Iterative Large 3D Reconstruction Model

August 3, 2025

Abdelrahman Mohamed이 [arXiv]에 게시한 ‘iLRM: An Iterative Large 3D Reconstruction Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vision-Language-Action Models

[논문리뷰] FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies

September 15, 2025

Fabian Otto이 [arXiv]에 게시한 ‘FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

September 12, 2025

Zirui Ge이 [arXiv]에 게시한 ‘VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control

September 1, 2025

Zhaoqing Chen이 [arXiv]에 게시한 ‘EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Do What? Teaching Vision-Language-Action Models to Reject the Impossible

August 25, 2025

Roei Herzig이 [arXiv]에 게시한 ‘Do What? Teaching Vision-Language-Action Models to Reject the Impossible’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models

August 3, 2025

Kaixin Wang이 [arXiv]에 게시한 ‘villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Robot Manipulation

[논문리뷰] Do You Need Proprioceptive States in Visuomotor Policies?

September 24, 2025

Yushen Liang이 [arXiv]에 게시한 ‘Do You Need Proprioceptive States in Visuomotor Policies?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

September 19, 2025

SpaceProduct이 [arXiv]에 게시한 ‘RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions

September 10, 2025

Zherui Qiu이 [arXiv]에 게시한 ‘F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] U-ARM : Ultra low-cost general teleoperation interface for robot manipulation

September 8, 2025

Junda Huang이 [arXiv]에 게시한 ‘U-ARM : Ultra low-cost general teleoperation interface for robot manipulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models

August 3, 2025

Kaixin Wang이 [arXiv]에 게시한 ‘villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Vision

[논문리뷰] 3D Aware Region Prompted Vision Language Model

September 17, 2025

Xiaolong Li이 [arXiv]에 게시한 ‘3D Aware Region Prompted Vision Language Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

September 12, 2025

Jian Gao이 [arXiv]에 게시한 ‘SpatialVID: A Large-Scale Video Dataset with Spatial Annotations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views

September 3, 2025

Junchi Yan이 [arXiv]에 게시한 ‘Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Vie...

[논문리뷰] MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting

August 26, 2025

Yanzhe Liang이 [arXiv]에 게시한 ‘MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Multimodal Referring Segmentation: A Survey

August 4, 2025

Zuxuan Wu이 [arXiv]에 게시한 ‘Multimodal Referring Segmentation: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Robotic Manipulation

[논문리뷰] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

September 12, 2025

Zhaohui Yang이 [arXiv]에 게시한 ‘SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation

August 20, 2025

Fei Ni이 [arXiv]에 게시한 ‘Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Precise Action-to-Video Generation Through Visual Action Prompts

August 19, 2025

Minghan Qin이 [arXiv]에 게시한 ‘Precise Action-to-Video Generation Through Visual Action Prompts’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation

August 8, 2025

Shengcong Chen이 [arXiv]에 게시한 ‘Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation

August 5, 2025

Yang Tian이 [arXiv]에 게시한 ‘InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Catastrophic Forgetting

[논문리뷰] The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward

September 12, 2025

Xiaoyu Tan이 [arXiv]에 게시한 ‘The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward’ 논문에 대한...

[논문리뷰] Provable Benefits of In-Tool Learning for Large Language Models

August 29, 2025

Vivien Cabannes이 [arXiv]에 게시한 ‘Provable Benefits of In-Tool Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay

August 13, 2025

Yang Fan이 [arXiv]에 게시한 ‘GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization

August 6, 2025

Aman Chadha이 [arXiv]에 게시한 ‘AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization...

[논문리뷰] InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation

August 5, 2025

Yang Tian이 [arXiv]에 게시한 ‘InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mixture-of-Experts (MoE)

[논문리뷰] EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence

September 19, 2025

Qinghua Huang이 [arXiv]에 게시한 ‘EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks

August 27, 2025

Daisuke Nohara이 [arXiv]에 게시한 ‘Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Intern-S1: A Scientific Multimodal Foundation Model

August 22, 2025

xuhuang87이 [arXiv]에 게시한 ‘Intern-S1: A Scientific Multimodal Foundation Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs

August 12, 2025

Jianguo Li이 [arXiv]에 게시한 ‘MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation

August 5, 2025

Yang Tian이 [arXiv]에 게시한 ‘InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Correction

[논문리뷰] THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning

September 18, 2025

Yicheng Pan이 [arXiv]에 게시한 ‘THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Interleaving Reasoning for Better Text-to-Image Generation

September 9, 2025

Shixiang Tang이 [arXiv]에 게시한 ‘Interleaving Reasoning for Better Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off

August 11, 2025

jgkwak이 [arXiv]에 게시한 ‘Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling

August 8, 2025

Ruolin Shen이 [arXiv]에 게시한 ‘Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling’ 논문에 대한 자세한 리뷰입...

[논문리뷰] Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction

August 6, 2025

Jui-Hui Chung이 [arXiv]에 게시한 ‘Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Diffusion Transformers

[논문리뷰] OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

September 23, 2025

Pengze Zhang이 [arXiv]에 게시한 ‘OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment

September 23, 2025

Yue Ma이 [arXiv]에 게시한 ‘ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EgoTwin: Dreaming Body and View in First Person

August 25, 2025

Wentao Wang이 [arXiv]에 게시한 ‘EgoTwin: Dreaming Body and View in First Person’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer

August 20, 2025

Deyu Zhou이 [arXiv]에 게시한 ‘Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework

August 7, 2025

Chao Liang이 [arXiv]에 게시한 ‘DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reward Hacking

[논문리뷰] RewardDance: Reward Scaling in Visual Generation

September 11, 2025

Liang Li이 [arXiv]에 게시한 ‘RewardDance: Reward Scaling in Visual Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

September 10, 2025

Yingfang Zhang이 [arXiv]에 게시한 ‘Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

August 29, 2025

Jiazi Bu이 [arXiv]에 게시한 ‘Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models

August 14, 2025

Guiyang Hou이 [arXiv]에 게시한 ‘Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards

August 7, 2025

Ling-I Wu이 [arXiv]에 게시한 ‘IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Math Reasoning

[논문리뷰] rStar2-Agent: Agentic Reasoning Technical Report

August 29, 2025

Weijiang Xu이 [arXiv]에 게시한 ‘rStar2-Agent: Agentic Reasoning Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models

August 14, 2025

Zhihan Zhou이 [arXiv]에 게시한 ‘MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models’ 논문에 대한 자세한 리뷰...

[논문리뷰] Aryabhata: An exam-focused language model for JEE Math

August 13, 2025

Sandeep Varma이 [arXiv]에 게시한 ‘Aryabhata: An exam-focused language model for JEE Math’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization

August 12, 2025

Guanting Dong이 [arXiv]에 게시한 ‘Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization

August 7, 2025

Kechi Zhang이 [arXiv]에 게시한 ‘RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization’ 논문에 대한 자세한 리뷰입...

Back to Top ↑

Long Context

[논문리뷰] Kwai Keye-VL 1.5 Technical Report

September 3, 2025

SXxtyz이 [arXiv]에 게시한 ‘Kwai Keye-VL 1.5 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

August 21, 2025

abercovich이 [arXiv]에 게시한 ‘NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers

August 21, 2025

Prathyusha Jwalapuram이 [arXiv]에 게시한 ‘MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning

August 7, 2025

Maksim Nekrashevich이 [arXiv]에 게시한 ‘Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management

August 7, 2025

Yunxin Liu이 [arXiv]에 게시한 ‘Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Supervised Fine-Tuning (SFT)

[논문리뷰] Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels

September 23, 2025

Qi Zhang이 [arXiv]에 게시한 ‘Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Improving Context Fidelity via Native Retrieval-Augmented Reasoning

September 18, 2025

Xiangru Tang이 [arXiv]에 게시한 ‘Improving Context Fidelity via Native Retrieval-Augmented Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Towards a Unified View of Large Language Model Post-Training

September 5, 2025

Hongyi Liu이 [arXiv]에 게시한 ‘Towards a Unified View of Large Language Model Post-Training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

August 8, 2025

Xinyu Ye이 [arXiv]에 게시한 ‘On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Are Today’s LLMs Ready to Explain Well-Being Concepts?

August 8, 2025

Huan Liu이 [arXiv]에 게시한 ‘Are Today’s LLMs Ready to Explain Well-Being Concepts?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Computer Vision

[논문리뷰] VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

September 24, 2025

Haoxiao Wang이 [arXiv]에 게시한 ‘VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

September 8, 2025

Wenzheng Chang이 [arXiv]에 게시한 ‘WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer

August 21, 2025

Jeremiah Jiang이 [arXiv]에 게시한 ‘Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation

August 8, 2025

Jian Yang이 [arXiv]에 게시한 ‘RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes

August 8, 2025

Xudong Jiang이 [arXiv]에 게시한 ‘MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Test-Time Scaling

[논문리뷰] MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction

September 23, 2025

Xintao Chen이 [arXiv]에 게시한 ‘MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving

September 17, 2025

Shansan Gong이 [arXiv]에 게시한 ‘EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet

September 9, 2025

See-Kiong Ng이 [arXiv]에 게시한 ‘Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Test-Time Reinforcement Learning for GUI Grounding via Region Consistency

August 13, 2025

Zhengxi Lu이 [arXiv]에 게시한 ‘Test-Time Reinforcement Learning for GUI Grounding via Region Consistency’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling

August 8, 2025

Ruolin Shen이 [arXiv]에 게시한 ‘Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling’ 논문에 대한 자세한 리뷰입...

Back to Top ↑

Progressive Training

[논문리뷰] OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

September 23, 2025

Pengze Zhang이 [arXiv]에 게시한 ‘OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SAIL-VL2 Technical Report

September 18, 2025

Zijian Kang이 [arXiv]에 게시한 ‘SAIL-VL2 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

September 12, 2025

Zhuowei Chen이 [arXiv]에 게시한 ‘HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AudioStory: Generating Long-Form Narrative Audio with Large Language Models

August 28, 2025

Yixiao Ge이 [arXiv]에 게시한 ‘AudioStory: Generating Long-Form Narrative Audio with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh

August 11, 2025

Yi Yang이 [arXiv]에 게시한 ‘MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Efficiency

[논문리뷰] MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction

September 23, 2025

Xintao Chen이 [arXiv]에 게시한 ‘MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models

September 3, 2025

Zhen Wang이 [arXiv]에 게시한 ‘FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning

September 1, 2025

Han Hu이 [arXiv]에 게시한 ‘R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning

August 12, 2025

Baihong Yuan이 [arXiv]에 게시한 ‘Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal

August 11, 2025

Chengcheng Wan이 [arXiv]에 게시한 ‘Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AI Safety

[논문리뷰] FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions

September 23, 2025

tengdai722이 [arXiv]에 게시한 ‘FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questio...

[논문리뷰] R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World

September 9, 2025

Bowen Zhou이 [arXiv]에 게시한 ‘R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize

September 5, 2025

Muhao Chen이 [arXiv]에 게시한 ‘False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Selection

August 20, 2025

Adriano Koshiyama이 [arXiv]에 게시한 ‘CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Select...

[논문리뷰] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

August 12, 2025

Xinhao Yi이 [arXiv]에 게시한 ‘A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems’ 논문에 대한 자세...

Back to Top ↑

Multimodal LLM

[논문리뷰] MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

September 22, 2025

jialingt이 [arXiv]에 게시한 ‘MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation

September 8, 2025

Zhan Zhao이 [arXiv]에 게시한 ‘LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UItron: Foundational GUI Agent with Advanced Perception and Planning

September 1, 2025

Yufeng Zhong이 [arXiv]에 게시한 ‘UItron: Foundational GUI Agent with Advanced Perception and Planning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models

August 14, 2025

Dongdong Zhang이 [arXiv]에 게시한 ‘VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents

August 12, 2025

Mohit Bansal이 [arXiv]에 게시한 ‘Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Zero-shot Learning

[논문리뷰] MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting

September 8, 2025

Vanessa Wildman이 [arXiv]에 게시한 ‘MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting’ 논...

[논문리뷰] From Editor to Dense Geometry Estimator

September 5, 2025

Lang Nie이 [arXiv]에 게시한 ‘From Editor to Dense Geometry Estimator’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Durian: Dual Reference-guided Portrait Animation with Attribute Transfer

September 5, 2025

Hanbyul Joo이 [arXiv]에 게시한 ‘Durian: Dual Reference-guided Portrait Animation with Attribute Transfer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang

September 3, 2025

Solomon Tsai이 [arXiv]에 게시한 ‘The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GLiClass: Generalist Lightweight Model for Sequence Classification Tasks

August 12, 2025

Alexander Yavorskyi이 [arXiv]에 게시한 ‘GLiClass: Generalist Lightweight Model for Sequence Classification Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning Tasks

[논문리뷰] Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

September 9, 2025

Ke Shen이 [arXiv]에 게시한 ‘Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks

August 27, 2025

Daisuke Nohara이 [arXiv]에 게시한 ‘Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment

August 26, 2025

Doratossadat Dastgheib이 [arXiv]에 게시한 ‘MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models

August 15, 2025

Qinghao Ye이 [arXiv]에 게시한 ‘Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning

August 12, 2025

Baihong Yuan이 [arXiv]에 게시한 ‘Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Imitation Learning

[논문리뷰] Do You Need Proprioceptive States in Visuomotor Policies?

September 24, 2025

Yushen Liang이 [arXiv]에 게시한 ‘Do You Need Proprioceptive States in Visuomotor Policies?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies

September 15, 2025

Fabian Otto이 [arXiv]에 게시한 ‘FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment

August 14, 2025

Lei Fan이 [arXiv]에 게시한 ‘Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance

August 14, 2025

Yong Li이 [arXiv]에 게시한 ‘AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation

August 12, 2025

Hengtao Shen이 [arXiv]에 게시한 ‘Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Compression

[논문리뷰] GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings

September 16, 2025

Yixuan Tang이 [arXiv]에 게시한 ‘GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling

September 10, 2025

Diana Marculescu이 [arXiv]에 게시한 ‘Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs

August 21, 2025

Haobo Xu이 [arXiv]에 게시한 ‘Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

August 21, 2025

abercovich이 [arXiv]에 게시한 ‘NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Survey on Diffusion Language Models

August 15, 2025

Zhiqiang Shen이 [arXiv]에 게시한 ‘A Survey on Diffusion Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Diffusion Models

[논문리뷰] Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

September 24, 2025

Yifeng Jiang이 [arXiv]에 게시한 ‘Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance

September 19, 2025

Ruibo Li이 [arXiv]에 게시한 ‘WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation

September 1, 2025

Qi Jia이 [arXiv]에 게시한 ‘Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models

August 27, 2025

Beiqi Chen이 [arXiv]에 게시한 ‘ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing

August 15, 2025

Xiaoyu Li이 [arXiv]에 게시한 ‘ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Latent Space

[논문리뷰] Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

September 22, 2025

Wenyu Wang이 [arXiv]에 게시한 ‘Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis

September 15, 2025

Song Guo이 [arXiv]에 게시한 ‘InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Collaborative Multi-Modal Coding for High-Quality 3D Generation

August 29, 2025

Ziwei Liu이 [arXiv]에 게시한 ‘Collaborative Multi-Modal Coding for High-Quality 3D Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space

August 27, 2025

Rui Chen이 [arXiv]에 게시한 ‘VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Next Visual Granularity Generation

August 19, 2025

Kang Liao이 [arXiv]에 게시한 ‘Next Visual Granularity Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Understanding

[논문리뷰] VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction

September 24, 2025

So Fukuda이 [arXiv]에 게시한 ‘VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe

September 24, 2025

Wenshuo Ma이 [arXiv]에 게시한 ‘MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents

September 22, 2025

Chao Zhang이 [arXiv]에 게시한 ‘Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Kwai Keye-VL 1.5 Technical Report

September 3, 2025

SXxtyz이 [arXiv]에 게시한 ‘Kwai Keye-VL 1.5 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RynnEC: Bringing MLLMs into Embodied World

August 21, 2025

jiangpinliu이 [arXiv]에 게시한 ‘RynnEC: Bringing MLLMs into Embodied World’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

RLVR

[논문리뷰] Single-stream Policy Optimization

September 17, 2025

Zihan Ding이 [arXiv]에 게시한 ‘Single-stream Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ΔL Normalization: Rethink Loss Aggregation in RLVR

September 10, 2025

Lili Qiu이 [arXiv]에 게시한 ‘ΔL Normalization: Rethink Loss Aggregation in RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding

September 10, 2025

Yongcheng Zeng이 [arXiv]에 게시한 ‘Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR

September 3, 2025

Lu Wang이 [arXiv]에 게시한 ‘Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DCPO: Dynamic Clipping Policy Optimization

September 3, 2025

Kai Lu이 [arXiv]에 게시한 ‘DCPO: Dynamic Clipping Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human-Computer Interaction

[논문리뷰] PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits

September 16, 2025

Zhenhao Chen이 [arXiv]에 게시한 ‘PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization

August 11, 2025

Pengxiang Li이 [arXiv]에 게시한 ‘InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Sel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generation

August 7, 2025

Hao Huang이 [arXiv]에 게시한 ‘Sel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations

August 3, 2025

Yiwen Guo이 [arXiv]에 게시한 ‘C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Attention Mechanisms

[논문리뷰] BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent

September 22, 2025

Jiahui Yang이 [arXiv]에 게시한 ‘BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Focusing by Contrastive Attention: Enhancing VLMs’ Visual Reasoning

September 9, 2025

Baolong Bi이 [arXiv]에 게시한 ‘Focusing by Contrastive Attention: Enhancing VLMs’ Visual Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer

August 6, 2025

Shunyu Yao이 [arXiv]에 게시한 ‘LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective

August 3, 2025

Eric C. Larson이 [arXiv]에 게시한 ‘On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Automated Theorem Proving

[논문리뷰] EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving

September 17, 2025

Shansan Gong이 [arXiv]에 게시한 ‘EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem

September 9, 2025

Damien Sileo이 [arXiv]에 게시한 ‘Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction

August 6, 2025

Jui-Hui Chung이 [arXiv]에 게시한 ‘Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving

August 3, 2025

Zhicheng Jiang이 [arXiv]에 게시한 ‘Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Iterative Refinement

[논문리뷰] Reverse-Engineered Reasoning for Open-Ended Generation

September 9, 2025

Wangchunshu Zhou이 [arXiv]에 게시한 ‘Reverse-Engineered Reasoning for Open-Ended Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists

August 22, 2025

Heng Zhang이 [arXiv]에 게시한 ‘aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HPSv3: Towards Wide-Spectrum Human Preference Score

August 7, 2025

Hongsheng Li이 [arXiv]에 게시한 ‘HPSv3: Towards Wide-Spectrum Human Preference Score’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] iLRM: An Iterative Large 3D Reconstruction Model

August 3, 2025

Abdelrahman Mohamed이 [arXiv]에 게시한 ‘iLRM: An Iterative Large 3D Reconstruction Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM-as-a-Judge

[논문리뷰] CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects

September 23, 2025

Hang Yu이 [arXiv]에 게시한 ‘CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge

August 20, 2025

Alice Wang이 [arXiv]에 게시한 ‘Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Are Today’s LLMs Ready to Explain Well-Being Concepts?

August 8, 2025

Huan Liu이 [arXiv]에 게시한 ‘Are Today’s LLMs Ready to Explain Well-Being Concepts?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges

August 4, 2025

Chengfei Lv이 [arXiv]에 게시한 ‘Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Preference Learning

[논문리뷰] LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

September 3, 2025

Jianwei Yang이 [arXiv]에 게시한 ‘LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment

August 14, 2025

Lei Fan이 [arXiv]에 게시한 ‘Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future

August 12, 2025

Qiufeng Wang이 [arXiv]에 게시한 ‘Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges

August 4, 2025

Chengfei Lv이 [arXiv]에 게시한 ‘Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image Synthesis

[논문리뷰] InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis

September 15, 2025

Song Guo이 [arXiv]에 게시한 ‘InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models

September 3, 2025

Zhen Wang이 [arXiv]에 게시한 ‘FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LightSwitch: Multi-view Relighting with Material-guided Diffusion

August 11, 2025

Shubham Tulsiani이 [arXiv]에 게시한 ‘LightSwitch: Multi-view Relighting with Material-guided Diffusion’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PixNerd: Pixel Neural Field Diffusion

August 4, 2025

Limin Wang이 [arXiv]에 게시한 ‘PixNerd: Pixel Neural Field Diffusion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning Models

[논문리뷰] Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated

September 12, 2025

Jamie Hayes이 [arXiv]에 게시한 ‘Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet

September 9, 2025

See-Kiong Ng이 [arXiv]에 게시한 ‘Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability

August 12, 2025

Yuchen Li이 [arXiv]에 게시한 ‘ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models’ Instruction Following

August 5, 2025

Jiaqing Liang이 [arXiv]에 게시한 ‘Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models’ Instruction Following’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hallucination Mitigation

[논문리뷰] SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge

September 10, 2025

Dipanjan Das이 [arXiv]에 게시한 ‘SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting

August 27, 2025

Manuela Veloso이 [arXiv]에 게시한 ‘QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Controlling Multimodal LLMs via Reward-guided Decoding

August 18, 2025

Michal Drozdzal이 [arXiv]에 게시한 ‘Controlling Multimodal LLMs via Reward-guided Decoding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ChartCap: Mitigating Hallucination of Dense Chart Captioning

August 6, 2025

Gunhee Kim이 [arXiv]에 게시한 ‘ChartCap: Mitigating Hallucination of Dense Chart Captioning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reward Model

[논문리뷰] RewardDance: Reward Scaling in Visual Generation

September 11, 2025

Liang Li이 [arXiv]에 게시한 ‘RewardDance: Reward Scaling in Visual Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

August 29, 2025

Jiazi Bu이 [arXiv]에 게시한 ‘Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models

August 14, 2025

Guiyang Hou이 [arXiv]에 게시한 ‘Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward

August 6, 2025

Songyang Gao이 [arXiv]에 게시한 ‘CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Automated Evaluation

[논문리뷰] FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games

September 3, 2025

Dongmin Park이 [arXiv]에 게시한 ‘FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis

August 28, 2025

Ion Stoica이 [arXiv]에 게시한 ‘DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis

August 8, 2025

Reshmi Ghosh이 [arXiv]에 게시한 ‘Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?

August 6, 2025

Yaojie Lu이 [arXiv]에 게시한 ‘LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Supervised Fine-tuning (SFT)

[논문리뷰] WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents

September 9, 2025

Aili Chen이 [arXiv]에 게시한 ‘WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information

August 19, 2025

Xi Yang이 [arXiv]에 게시한 ‘Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities

August 8, 2025

Zhijie Sang이 [arXiv]에 게시한 ‘InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Tool-integrated Reinforcement Learning for Repo Deep Search

August 6, 2025

Yanzhen Zou이 [arXiv]에 게시한 ‘Tool-integrated Reinforcement Learning for Repo Deep Search’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-modal Learning

[논문리뷰] PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era

September 18, 2025

Zihao Dongfang이 [arXiv]에 게시한 ‘PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings

September 5, 2025

Meie Fang이 [arXiv]에 게시한 ‘Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Collaborative Multi-Modal Coding for High-Quality 3D Generation

August 29, 2025

Ziwei Liu이 [arXiv]에 게시한 ‘Collaborative Multi-Modal Coding for High-Quality 3D Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding

August 7, 2025

Jianke Zhu이 [arXiv]에 게시한 ‘A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Variational Autoencoder

[논문리뷰] WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers

September 22, 2025

Karun Kumar이 [arXiv]에 게시한 ‘WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VibeVoice Technical Report

August 27, 2025

Yaoyao Chang이 [arXiv]에 게시한 ‘VibeVoice Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms

August 15, 2025

Ziyin Zhang이 [arXiv]에 게시한 ‘From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms’ 논문에 대한 자세한 ...

[논문리뷰] Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

August 7, 2025

Feng Zhao이 [arXiv]에 게시한 ‘Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Verifiable Rewards

[논문리뷰] Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning

September 23, 2025

Damien Sileo이 [arXiv]에 게시한 ‘Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Survey of Reinforcement Learning for Large Reasoning Models

September 11, 2025

Runze Liu이 [arXiv]에 게시한 ‘A Survey of Reinforcement Learning for Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models

August 14, 2025

Guiyang Hou이 [arXiv]에 게시한 ‘Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards

August 7, 2025

Ling-I Wu이 [arXiv]에 게시한 ‘IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Efficient Inference

[논문리뷰] MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe

September 24, 2025

Wenshuo Ma이 [arXiv]에 게시한 ‘MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Causal Attention with Lookahead Keys

September 10, 2025

Quanquan Gu이 [arXiv]에 게시한 ‘Causal Attention with Lookahead Keys’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning

August 27, 2025

Ran Guo이 [arXiv]에 게시한 ‘UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MiDashengLM: Efficient Audio Understanding with General Audio Captions

August 7, 2025

Yadong Niu이 [arXiv]에 게시한 ‘MiDashengLM: Efficient Audio Understanding with General Audio Captions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Open-Source

[논문리뷰] ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

September 19, 2025

Zehao Li이 [arXiv]에 게시한 ‘ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Wan-Animate: Unified Character Animation and Replacement with Holistic Replication

September 18, 2025

Mingyang Huang이 [arXiv]에 게시한 ‘Wan-Animate: Unified Character Animation and Replacement with Holistic Replication’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

August 26, 2025

jinglinglin이 [arXiv]에 게시한 ‘InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets

August 7, 2025

MaziyarPanahi이 [arXiv]에 게시한 ‘OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets’ 논문에 대한 자세한 ...

Back to Top ↑

Direct Preference Optimization (DPO)

[논문리뷰] Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD

August 29, 2025

Roy Ka-Wei Lee이 [arXiv]에 게시한 ‘Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future

August 12, 2025

Qiufeng Wang이 [arXiv]에 게시한 ‘Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities

August 8, 2025

Zhijie Sang이 [arXiv]에 게시한 ‘InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Are Today’s LLMs Ready to Explain Well-Being Concepts?

August 8, 2025

Huan Liu이 [arXiv]에 게시한 ‘Are Today’s LLMs Ready to Explain Well-Being Concepts?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GUI Automation

[논문리뷰] ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

September 19, 2025

Zehao Li이 [arXiv]에 게시한 ‘ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning

September 16, 2025

Yongliang Shen이 [arXiv]에 게시한 ‘UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mobile-Agent-v3: Foundamental Agents for GUI Automation

August 22, 2025

Haowei Liu이 [arXiv]에 게시한 ‘Mobile-Agent-v3: Foundamental Agents for GUI Automation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CoAct-1: Computer-using Agents with Coding as Actions

August 8, 2025

Taiwei Shi이 [arXiv]에 게시한 ‘CoAct-1: Computer-using Agents with Coding as Actions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fairness

[논문리뷰] AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models

September 3, 2025

Rahul Karthikeyan이 [arXiv]에 게시한 ‘AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Al...

[논문리뷰] AHELM: A Holistic Evaluation of Audio-Language Models

September 1, 2025

Siwei Yang이 [arXiv]에 게시한 ‘AHELM: A Holistic Evaluation of Audio-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

August 12, 2025

Kai Zou이 [arXiv]에 게시한 ‘BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations

August 8, 2025

Chirag Shah이 [arXiv]에 게시한 ‘I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations’ 논문에...

Back to Top ↑

Policy Gradient

[논문리뷰] Single-stream Policy Optimization

September 17, 2025

Zihan Ding이 [arXiv]에 게시한 ‘Single-stream Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ΔL Normalization: Rethink Loss Aggregation in RLVR

September 10, 2025

Lili Qiu이 [arXiv]에 게시한 ‘ΔL Normalization: Rethink Loss Aggregation in RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Towards a Unified View of Large Language Model Post-Training

September 5, 2025

Hongyi Liu이 [arXiv]에 게시한 ‘Towards a Unified View of Large Language Model Post-Training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

August 8, 2025

Xinyu Ye이 [arXiv]에 게시한 ‘On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Low-Resource Languages

[논문리뷰] Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

September 23, 2025

Fatma Betül Terzioğlu이 [arXiv]에 게시한 ‘Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Hunyuan-MT Technical Report

September 11, 2025

Yang Du이 [arXiv]에 게시한 ‘Hunyuan-MT Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?

August 21, 2025

Daeyoung Kim이 [arXiv]에 게시한 ‘ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs

August 11, 2025

Guohang Yan이 [arXiv]에 게시한 ‘MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GUI Agents

[논문리뷰] MobiAgent: A Systematic Framework for Customizable Mobile Agents

September 3, 2025

Wangbo Gong이 [arXiv]에 게시한 ‘MobiAgent: A Systematic Framework for Customizable Mobile Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games

September 3, 2025

Dongmin Park이 [arXiv]에 게시한 ‘FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

August 28, 2025

Jianze Liang이 [arXiv]에 게시한 ‘CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning’ 논문에 대한 ...

[논문리뷰] UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding

August 11, 2025

Bingqi Chen이 [arXiv]에 게시한 ‘UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Virtual Try-On

[논문리뷰] FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models

September 3, 2025

Zhen Wang이 [arXiv]에 게시한 ‘FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Dress&Dance: Dress up and Dance as You Like It - Technical Preview

August 29, 2025

Yu-Xiong Wang이 [arXiv]에 게시한 ‘Dress&Dance: Dress up and Dance as You Like It - Technical Preview’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniTry: Virtual Try-On Anything without Masks

August 20, 2025

Xiaoduan Feng이 [arXiv]에 게시한 ‘OmniTry: Virtual Try-On Anything without Masks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off

August 11, 2025

jgkwak이 [arXiv]에 게시한 ‘Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Attention Mechanism

[논문리뷰] FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection

September 19, 2025

Zhewei Zhang이 [arXiv]에 게시한 ‘FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation

September 12, 2025

Dong-Ho Lee이 [arXiv]에 게시한 ‘Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Limitations of Normalization in Attention Mechanism

August 26, 2025

Radu State이 [arXiv]에 게시한 ‘Limitations of Normalization in Attention Mechanism’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off

August 11, 2025

jgkwak이 [arXiv]에 게시한 ‘Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Retrieval Augmented Generation

[논문리뷰] Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

September 23, 2025

Fatma Betül Terzioğlu이 [arXiv]에 게시한 ‘Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MV-RAG: Retrieval Augmented Multiview Diffusion

August 26, 2025

sagiebenaim이 [arXiv]에 게시한 ‘MV-RAG: Retrieval Augmented Multiview Diffusion’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Semantic IDs for Joint Generative Search and Recommendation

August 20, 2025

Enrico Palumbo이 [arXiv]에 게시한 ‘Semantic IDs for Joint Generative Search and Recommendation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System

August 12, 2025

Reynold Cheng이 [arXiv]에 게시한 ‘Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Few-shot Learning

[논문리뷰] Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence

August 20, 2025

Xin Chen이 [arXiv]에 게시한 ‘Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Leveraging Large Language Models for Predictive Analysis of Human Misery

August 20, 2025

Abhilash Nandy이 [arXiv]에 게시한 ‘Leveraging Large Language Models for Predictive Analysis of Human Misery’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation

August 18, 2025

Paolo Soda이 [arXiv]에 게시한 ‘SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GLiClass: Generalist Lightweight Model for Sequence Classification Tasks

August 12, 2025

Alexander Yavorskyi이 [arXiv]에 게시한 ‘GLiClass: Generalist Lightweight Model for Sequence Classification Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bias Mitigation

[논문리뷰] SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

September 18, 2025

Zhun Wang이 [arXiv]에 게시한 ‘SteeringControl: Holistic Evaluation of Alignment Steering in LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models

September 3, 2025

Rahul Karthikeyan이 [arXiv]에 게시한 ‘AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Al...

[논문리뷰] CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Selection

August 20, 2025

Adriano Koshiyama이 [arXiv]에 게시한 ‘CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Select...

[논문리뷰] BiasGym: Fantastic Biases and How to Find (and Remove) Them

August 13, 2025

Arnav Arora이 [arXiv]에 게시한 ‘BiasGym: Fantastic Biases and How to Find (and Remove) Them’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mechanistic Interpretability

[논문리뷰] Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection

August 29, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Transcription: Mechanistic Interpretability in ASR

August 28, 2025

Aviv Shamsian이 [arXiv]에 게시한 ‘Beyond Transcription: Mechanistic Interpretability in ASR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Selection

August 20, 2025

Adriano Koshiyama이 [arXiv]에 게시한 ‘CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Select...

[논문리뷰] BiasGym: Fantastic Biases and How to Find (and Remove) Them

August 13, 2025

Arnav Arora이 [arXiv]에 게시한 ‘BiasGym: Fantastic Biases and How to Find (and Remove) Them’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Diffusion Language Models

[논문리뷰] Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

September 9, 2025

Ke Shen이 [arXiv]에 게시한 ‘Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Diffusion Language Models Know the Answer Before Decoding

August 28, 2025

Shilin Yan이 [arXiv]에 게시한 ‘Diffusion Language Models Know the Answer Before Decoding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Survey on Diffusion Language Models

August 15, 2025

Zhiqiang Shen이 [arXiv]에 게시한 ‘A Survey on Diffusion Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models

August 13, 2025

Chenchen Jing이 [arXiv]에 게시한 ‘Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text Generation

[논문리뷰] A Survey on Diffusion Language Models

August 15, 2025

Zhiqiang Shen이 [arXiv]에 게시한 ‘A Survey on Diffusion Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing

August 14, 2025

Hao Zhang이 [arXiv]에 게시한 ‘Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study

August 14, 2025

Gjergji Kasneci이 [arXiv]에 게시한 ‘Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models

August 13, 2025

Chenchen Jing이 [arXiv]에 게시한 ‘Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Diffusion LLMs

[논문리뷰] Inpainting-Guided Policy Optimization for Diffusion Large Language Models

September 15, 2025

Chenyu Wang이 [arXiv]에 게시한 ‘Inpainting-Guided Policy Optimization for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs

August 21, 2025

Haobo Xu이 [arXiv]에 게시한 ‘Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Speed Always Wins: A Survey on Efficient Architectures for Large Language Models

August 19, 2025

Jusen Du이 [arXiv]에 게시한 ‘Speed Always Wins: A Survey on Efficient Architectures for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing

August 14, 2025

Hao Zhang이 [arXiv]에 게시한 ‘Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Identity Preservation

[논문리뷰] Lynx: Towards High-Fidelity Personalized Video Generation

September 22, 2025

Linjie Luo이 [arXiv]에 게시한 ‘Lynx: Towards High-Fidelity Personalized Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence

September 16, 2025

Lionel M. Ni이 [arXiv]에 게시한 ‘LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement

September 4, 2025

Hualiang Wang이 [arXiv]에 게시한 ‘MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation

August 14, 2025

Chen Li이 [arXiv]에 게시한 ‘Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

CLIP

[논문리뷰] Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval

September 12, 2025

Kaicheng Yang이 [arXiv]에 게시한 ‘Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CLIPSym: Delving into Symmetry Detection with CLIP

September 1, 2025

Raymond A. Yeh이 [arXiv]에 게시한 ‘CLIPSym: Delving into Symmetry Detection with CLIP’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Selective Contrastive Learning for Weakly Supervised Affordance Grounding

August 25, 2025

Jae-Pil Heo이 [arXiv]에 게시한 ‘Selective Contrastive Learning for Weakly Supervised Affordance Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Processing and acquisition traces in visual encoders: What does CLIP know about your camera?

August 15, 2025

Giorgos Tolias이 [arXiv]에 게시한 ‘Processing and acquisition traces in visual encoders: What does CLIP know about your camera?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vision Transformer

[논문리뷰] Curia: A Multi-Modal Foundation Model for Radiology

September 10, 2025

Elodie Ferreres이 [arXiv]에 게시한 ‘Curia: A Multi-Modal Foundation Model for Radiology’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Does DINOv3 Set a New Medical Vision Standard?

September 9, 2025

Bailiang Jian이 [arXiv]에 게시한 ‘Does DINOv3 Set a New Medical Vision Standard?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision

September 3, 2025

Yan-Jie Zhou이 [arXiv]에 게시한 ‘M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DINOv3

August 18, 2025

Maxime Oquab이 [arXiv]에 게시한 ‘DINOv3’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Medical Imaging

[논문리뷰] Does DINOv3 Set a New Medical Vision Standard?

September 9, 2025

Bailiang Jian이 [arXiv]에 게시한 ‘Does DINOv3 Set a New Medical Vision Standard?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting

September 8, 2025

Vanessa Wildman이 [arXiv]에 게시한 ‘MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting’ 논...

[논문리뷰] X-Node: Self-Explanation is All We Need

August 18, 2025

Islem Rekik이 [arXiv]에 게시한 ‘X-Node: Self-Explanation is All We Need’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation

August 18, 2025

Paolo Soda이 [arXiv]에 게시한 ‘SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Reasoning

[논문리뷰] Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models

September 16, 2025

Shuo Ren이 [arXiv]에 게시한 ‘Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforced Visual Perception with Tools

September 9, 2025

Mingyang Fu이 [arXiv]에 게시한 ‘Reinforced Visual Perception with Tools’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Focusing by Contrastive Attention: Enhancing VLMs’ Visual Reasoning

September 9, 2025

Baolong Bi이 [arXiv]에 게시한 ‘Focusing by Contrastive Attention: Enhancing VLMs’ Visual Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Thyme: Think Beyond Images

August 18, 2025

Wei Chen이 [arXiv]에 게시한 ‘Thyme: Think Beyond Images’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Camera Pose Estimation

[논문리뷰] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

September 12, 2025

Jian Gao이 [arXiv]에 게시한 ‘SpatialVID: A Large-Scale Video Dataset with Spatial Annotations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

September 8, 2025

Wenzheng Chang이 [arXiv]에 게시한 ‘WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

August 20, 2025

Yen-Yu Lin이 [arXiv]에 게시한 ‘LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration

August 19, 2025

Evgeny Burnaev이 [arXiv]에 게시한 ‘G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Depth Estimation

[논문리뷰] 3D Aware Region Prompted Vision Language Model

September 17, 2025

Xiaolong Li이 [arXiv]에 게시한 ‘3D Aware Region Prompted Vision Language Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From Editor to Dense Geometry Estimator

September 5, 2025

Lang Nie이 [arXiv]에 게시한 ‘From Editor to Dense Geometry Estimator’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Multi-View 3D Point Tracking

August 29, 2025

Irem Demir이 [arXiv]에 게시한 ‘Multi-View 3D Point Tracking’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration

August 19, 2025

Evgeny Burnaev이 [arXiv]에 게시한 ‘G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agentic Reinforcement Learning

[논문리뷰] VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use

September 3, 2025

Zhiheng Lyu이 [arXiv]에 게시한 ‘VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

September 3, 2025

Hejia Geng이 [arXiv]에 게시한 ‘The Landscape of Agentic Reinforcement Learning for LLMs: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] rStar2-Agent: Agentic Reasoning Technical Report

August 29, 2025

Weijiang Xu이 [arXiv]에 게시한 ‘rStar2-Agent: Agentic Reasoning Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

August 20, 2025

Liam-Liu이 [arXiv]에 게시한 ‘Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

RLHF

[논문리뷰] BaseReward: A Strong Baseline for Multimodal Reward Model

September 22, 2025

jianfeipan이 [arXiv]에 게시한 ‘BaseReward: A Strong Baseline for Multimodal Reward Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RewardDance: Reward Scaling in Visual Generation

September 11, 2025

Liang Li이 [arXiv]에 게시한 ‘RewardDance: Reward Scaling in Visual Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models

August 22, 2025

Lifan Guo이 [arXiv]에 게시한 ‘Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

August 21, 2025

Yu Lu이 [arXiv]에 게시한 ‘DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Context Protocol (MCP)

[논문리뷰] MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools

September 15, 2025

Xiaorui Wang이 [arXiv]에 게시한 ‘MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents

September 9, 2025

James Zou이 [arXiv]에 게시한 ‘Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

August 29, 2025

Shashank Biju이 [arXiv]에 게시한 ‘MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries

August 22, 2025

huuuyeah이 [arXiv]에 게시한 ‘LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GUI Agent

[논문리뷰] Mano Report

September 23, 2025

Minghui Wu이 [arXiv]에 게시한 ‘Mano Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent

September 22, 2025

Jiahui Yang이 [arXiv]에 게시한 ‘BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

September 3, 2025

Haoyang Zou이 [arXiv]에 게시한 ‘UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UItron: Foundational GUI Agent with Advanced Perception and Planning

September 1, 2025

Yufeng Zhong이 [arXiv]에 게시한 ‘UItron: Foundational GUI Agent with Advanced Perception and Planning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long-Horizon Tasks

[논문리뷰] SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

September 23, 2025

Yannis Yiming He이 [arXiv]에 게시한 ‘SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents

September 17, 2025

Wenbiao Yin이 [arXiv]에 게시한 ‘WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs

September 15, 2025

Jonas Geiping이 [arXiv]에 게시한 ‘The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents

September 12, 2025

Xintao Wang이 [arXiv]에 게시한 ‘Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Online RL

[논문리뷰] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

September 23, 2025

Qinsheng Zhang이 [arXiv]에 게시한 ‘DiffusionNFT: Online Diffusion Reinforcement with Forward Process’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning

September 16, 2025

Yongliang Shen이 [arXiv]에 게시한 ‘UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting

September 16, 2025

Changlong Yu이 [arXiv]에 게시한 ‘Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

September 12, 2025

Zhaohui Yang이 [arXiv]에 게시한 ‘SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Me

[AWS] AWS Solutions Architect Associate 자격증 취득 후기

March 8, 2025

AWS Solutions Architect Associate(SAA) 자격증 공부 방법, 시험 후기를 정리했습니다.

뇌과학적으로 게으름과 무기력을 극복하는 방법

February 25, 2025

게으름과 무기력은 단순한 의지 부족이 아니라, 뇌의 작동 방식과 깊은 관련이 있습니다. 전두엽을 활성화하고, 불필요한 정보를 차단하며, 긍정적인 자기 암시를 활용하는 방법을 통해 효율적으로 극복하는 법을 알아보세요.

블로그 개발 완료

January 1, 2025

새해 첫날, 기술 블로그 작성을 시작하다

Back to Top ↑

Jenkins

[Jenkins] 무중단 배포를 위한 파이프라인 구성

January 18, 2025

Jenkins를 이용한 무중단 배포 방법을 공유합니다.

[Jenkins] Jenkins 파이프라인 생성

January 8, 2025

Jenkins 파이프라인 생성 방법을 공유합니다.

[Jenkins] Jenkins 초기 설정

January 7, 2025

Jenkins 초기 설정 방법을 공유합니다.

Back to Top ↑

Knowledge Distillation

[논문리뷰] NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

August 21, 2025

abercovich이 [arXiv]에 게시한 ‘NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay

August 13, 2025

Yang Fan이 [arXiv]에 게시한 ‘GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification

August 3, 2025

Abdelmalik Taleb-Ahmed이 [arXiv]에 게시한 ‘Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification’ 논문에 대한 ...

Back to Top ↑

Transformer Models

[논문리뷰] CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media

September 16, 2025

Subasish Das이 [arXiv]에 게시한 ‘CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Limitations of Normalization in Attention Mechanism

August 26, 2025

Radu State이 [arXiv]에 게시한 ‘Limitations of Normalization in Attention Mechanism’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Enhanced Arabic Text Retrieval with Attentive Relevance Scoring

August 3, 2025

Abdenour Hadid이 [arXiv]에 게시한 ‘Enhanced Arabic Text Retrieval with Attentive Relevance Scoring’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Residual Learning

[논문리뷰] Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics

August 25, 2025

Xiao Sun이 [arXiv]에 게시한 ‘Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension

August 5, 2025

Liyan Xu이 [arXiv]에 게시한 ‘SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NeRF Is a Valuable Assistant for 3D Gaussian Splatting

August 3, 2025

ZeSheng Wang이 [arXiv]에 게시한 ‘NeRF Is a Valuable Assistant for 3D Gaussian Splatting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Recommender Systems

[논문리뷰] Understanding Embedding Scaling in Collaborative Filtering

September 23, 2025

Yonghui Yang이 [arXiv]에 게시한 ‘Understanding Embedding Scaling in Collaborative Filtering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge

August 20, 2025

Alice Wang이 [arXiv]에 게시한 ‘Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RecGPT Technical Report

August 3, 2025

Jian Wu이 [arXiv]에 게시한 ‘RecGPT Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human-in-the-Loop

[논문리뷰] A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning

September 22, 2025

Jiangmiao이 [arXiv]에 게시한 ‘A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?

August 21, 2025

Daeyoung Kim이 [arXiv]에 게시한 ‘ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RecGPT Technical Report

August 3, 2025

Jian Wu이 [arXiv]에 게시한 ‘RecGPT Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Task Learning

[논문리뷰] OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning

August 29, 2025

Yitong Wang이 [arXiv]에 게시한 ‘OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Semantic IDs for Joint Generative Search and Recommendation

August 20, 2025

Enrico Palumbo이 [arXiv]에 게시한 ‘Semantic IDs for Joint Generative Search and Recommendation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents

August 3, 2025

Anji Liu이 [arXiv]에 게시한 ‘Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-task Learning

[논문리뷰] MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks

September 19, 2025

Xijun Gu이 [arXiv]에 게시한 ‘MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering

August 7, 2025

Ambuj Mehrish이 [arXiv]에 게시한 ‘SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

August 4, 2025

Hao Tang이 [arXiv]에 게시한 ‘3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Survey

[논문리뷰] Explain Before You Answer: A Survey on Compositional Visual Reasoning

August 26, 2025

Xin Zheng이 [arXiv]에 게시한 ‘Explain Before You Answer: A Survey on Compositional Visual Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

August 12, 2025

Xinhao Yi이 [arXiv]에 게시한 ‘A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems’ 논문에 대한 자세...

[논문리뷰] Multimodal Referring Segmentation: A Survey

August 4, 2025

Zuxuan Wu이 [arXiv]에 게시한 ‘Multimodal Referring Segmentation: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

MLLM

[논문리뷰] Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval

September 12, 2025

Kaicheng Yang이 [arXiv]에 게시한 ‘Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UI-Venus Technical Report: Building High-performance UI Agents with RFT

August 15, 2025

Shuheng Shen이 [arXiv]에 게시한 ‘UI-Venus Technical Report: Building High-performance UI Agents with RFT’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation

August 4, 2025

Long Chen이 [arXiv]에 게시한 ‘SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Training-free

[논문리뷰] Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing

September 3, 2025

Amin Heyrani Nobar이 [arXiv]에 게시한 ‘Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence

August 20, 2025

Xin Chen이 [arXiv]에 게시한 ‘Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation

August 4, 2025

Long Chen이 [arXiv]에 게시한 ‘SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

VQA

[논문리뷰] When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs

September 23, 2025

Anand Mishra이 [arXiv]에 게시한 ‘When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs’ 논문에...

[논문리뷰] EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence

September 19, 2025

Qinghua Huang이 [arXiv]에 게시한 ‘EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models

August 5, 2025

Zuxuan Wu이 [arXiv]에 게시한 ‘A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Exploration-Exploitation

[논문리뷰] AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning

September 11, 2025

Honglin Guo이 [arXiv]에 게시한 ‘AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models

August 15, 2025

Qinghao Ye이 [arXiv]에 게시한 ‘Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Exploitation Is All You Need… for Exploration

August 5, 2025

Jesse Roberts이 [arXiv]에 게시한 ‘Exploitation Is All You Need… for Exploration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-Attention

[논문리뷰] Lynx: Towards High-Fidelity Personalized Video Generation

September 22, 2025

Linjie Luo이 [arXiv]에 게시한 ‘Lynx: Towards High-Fidelity Personalized Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection

September 3, 2025

Vito Renó이 [arXiv]에 게시한 ‘C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Personalized Safety Alignment for Text-to-Image Diffusion Models

August 5, 2025

Kaidong Yu이 [arXiv]에 게시한 ‘Personalized Safety Alignment for Text-to-Image Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Safety Alignment

[논문리뷰] Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD

August 29, 2025

Roy Ka-Wei Lee이 [arXiv]에 게시한 ‘Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] BiasGym: Fantastic Biases and How to Find (and Remove) Them

August 13, 2025

Arnav Arora이 [arXiv]에 게시한 ‘BiasGym: Fantastic Biases and How to Find (and Remove) Them’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Personalized Safety Alignment for Text-to-Image Diffusion Models

August 5, 2025

Kaidong Yu이 [arXiv]에 게시한 ‘Personalized Safety Alignment for Text-to-Image Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Lifelong Learning

[논문리뷰] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

August 12, 2025

Xinhao Yi이 [arXiv]에 게시한 ‘A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems’ 논문에 대한 자세...

[논문리뷰] Memp: Exploring Agent Procedural Memory

August 11, 2025

Shuofei Qiao이 [arXiv]에 게시한 ‘Memp: Exploring Agent Procedural Memory’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Lifelong Learning in Physical Embodied Systems

August 5, 2025

Junkun Hong이 [arXiv]에 게시한 ‘RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Lifelong Learning in Physical Embodied Systems’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fine-Tuning

[논문리뷰] When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs

August 19, 2025

Elena Tutubalina이 [arXiv]에 게시한 ‘When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation

August 13, 2025

Rachel Bawden이 [arXiv]에 게시한 ‘TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization

August 6, 2025

Aman Chadha이 [arXiv]에 게시한 ‘AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization...

Back to Top ↑

LLM Safety

[논문리뷰] False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize

September 5, 2025

Muhao Chen이 [arXiv]에 게시한 ‘False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection

August 29, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization

August 6, 2025

Aman Chadha이 [arXiv]에 게시한 ‘AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization...

Back to Top ↑

Dataset Generation

[논문리뷰] German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German

August 26, 2025

Cristian-George Craciun이 [arXiv]에 게시한 ‘German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models

August 19, 2025

Zixiang Gao이 [arXiv]에 게시한 ‘Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ChartCap: Mitigating Hallucination of Dense Chart Captioning

August 6, 2025

Gunhee Kim이 [arXiv]에 게시한 ‘ChartCap: Mitigating Hallucination of Dense Chart Captioning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Inference

[논문리뷰] PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits

September 16, 2025

Zhenhao Chen이 [arXiv]에 게시한 ‘PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference

August 28, 2025

Chunlei Han이 [arXiv]에 게시한 ‘Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

August 6, 2025

Fan Xia이 [arXiv]에 게시한 ‘Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Parameter Efficiency

[논문리뷰] Provable Benefits of In-Tool Learning for Large Language Models

August 29, 2025

Vivien Cabannes이 [arXiv]에 게시한 ‘Provable Benefits of In-Tool Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs

August 12, 2025

Jianguo Li이 [arXiv]에 게시한 ‘MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation

August 6, 2025

Tianyidan Xie이 [arXiv]에 게시한 ‘Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reinforcement Learning from Human Feedback

[논문리뷰] A Survey on Diffusion Language Models

August 15, 2025

Zhiqiang Shen이 [arXiv]에 게시한 ‘A Survey on Diffusion Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment

August 14, 2025

Lei Fan이 [arXiv]에 게시한 ‘Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TRACEALIGN – Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs

August 6, 2025

Aman Chadha이 [arXiv]에 게시한 ‘TRACEALIGN – Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Framework

[논문리뷰] VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use

September 3, 2025

Zhiheng Lyu이 [arXiv]에 게시한 ‘VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications

August 25, 2025

Liuyi Yao이 [arXiv]에 게시한 ‘AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Agent Lightning: Train ANY AI Agents with Reinforcement Learning

August 7, 2025

Zilong Wang이 [arXiv]에 게시한 ‘Agent Lightning: Train ANY AI Agents with Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Markov Decision Process

[논문리뷰] WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents

September 17, 2025

Wenbiao Yin이 [arXiv]에 게시한 ‘WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models

August 20, 2025

Zishang Jiang이 [arXiv]에 게시한 ‘A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Agent Lightning: Train ANY AI Agents with Reinforcement Learning

August 7, 2025

Zilong Wang이 [arXiv]에 게시한 ‘Agent Lightning: Train ANY AI Agents with Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Continual Learning

[논문리뷰] R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World

September 9, 2025

Bowen Zhou이 [arXiv]에 게시한 ‘R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay

August 13, 2025

Yang Fan이 [arXiv]에 게시한 ‘GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor

August 7, 2025

Jinbao Wang이 [arXiv]에 게시한 ‘C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GAIA Benchmark

[논문리뷰] AWorld: Orchestrating the Training Recipe for Agentic AI

August 29, 2025

Qintong Wu이 [arXiv]에 게시한 ‘AWorld: Orchestrating the Training Recipe for Agentic AI’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving

August 14, 2025

Jinjie Gu이 [arXiv]에 게시한 ‘AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Efficient Agents: Building Effective Agents While Reducing Cost

August 7, 2025

Yue Hou이 [arXiv]에 게시한 ‘Efficient Agents: Building Effective Agents While Reducing Cost’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

PPO

[논문리뷰] Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization

August 12, 2025

Guanting Dong이 [arXiv]에 게시한 ‘Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GLiClass: Generalist Lightweight Model for Sequence Classification Tasks

August 12, 2025

Alexander Yavorskyi이 [arXiv]에 게시한 ‘GLiClass: Generalist Lightweight Model for Sequence Classification Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success

August 7, 2025

Ruslan Rakhimov이 [arXiv]에 게시한 ‘Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success’ 논문에 대한 자세한 리뷰...

Back to Top ↑

Chain-of-Thought (CoT)

[논문리뷰] CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning

August 25, 2025

Yulun Zhang이 [arXiv]에 게시한 ‘CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning’ 논문에 대한 자세한 리뷰...

[논문리뷰] Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents

August 7, 2025

Xinyu Yang이 [arXiv]에 게시한 ‘Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LaTCoder: Converting Webpage Design to Code with Layout-as-Thought

August 7, 2025

Tianpeng Lv이 [arXiv]에 게시한 ‘LaTCoder: Converting Webpage Design to Code with Layout-as-Thought’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

KV Cache Optimization

[논문리뷰] Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing

August 14, 2025

Hao Zhang이 [arXiv]에 게시한 ‘Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning

August 12, 2025

Baihong Yuan이 [arXiv]에 게시한 ‘Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LeanK: Learnable K Cache Channel Pruning for Efficient Decoding

August 7, 2025

Yuqing Yang이 [arXiv]에 게시한 ‘LeanK: Learnable K Cache Channel Pruning for Efficient Decoding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Speech Recognition

[논문리뷰] NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations

August 13, 2025

Haoyue Zhan이 [arXiv]에 게시한 ‘NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition

August 13, 2025

Lukáš Burget이 [arXiv]에 게시한 ‘DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MiDashengLM: Efficient Audio Understanding with General Audio Captions

August 7, 2025

Yadong Niu이 [arXiv]에 게시한 ‘MiDashengLM: Efficient Audio Understanding with General Audio Captions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Exploration

[논문리뷰] Inpainting-Guided Policy Optimization for Diffusion Large Language Models

September 15, 2025

Chenyu Wang이 [arXiv]에 게시한 ‘Inpainting-Guided Policy Optimization for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance

August 14, 2025

Yong Li이 [arXiv]에 게시한 ‘AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization

August 7, 2025

Kechi Zhang이 [arXiv]에 게시한 ‘RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization’ 논문에 대한 자세한 리뷰입...

Back to Top ↑

Speech Synthesis

[논문리뷰] VibeVoice Technical Report

August 27, 2025

Yaoyao Chang이 [arXiv]에 게시한 ‘VibeVoice Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations

August 13, 2025

Haoyue Zhan이 [arXiv]에 게시한 ‘NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Marco-Voice Technical Report

August 8, 2025

Qingjuan Li이 [arXiv]에 게시한 ‘Marco-Voice Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-to-Speech

[논문리뷰] TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling

August 26, 2025

Jiaqi Li이 [arXiv]에 게시한 ‘TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations

August 13, 2025

Haoyue Zhan이 [arXiv]에 게시한 ‘NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Marco-Voice Technical Report

August 8, 2025

Qingjuan Li이 [arXiv]에 게시한 ‘Marco-Voice Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Play

[논문리뷰] Language Self-Play For Data-Free Training

September 10, 2025

Vijai Mohan이 [arXiv]에 게시한 ‘Language Self-Play For Data-Free Training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

August 25, 2025

Ying Nian Wu이 [arXiv]에 게시한 ‘Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] R-Zero: Self-Evolving Reasoning LLM from Zero Data

August 8, 2025

Zongxia Li이 [arXiv]에 게시한 ‘R-Zero: Self-Evolving Reasoning LLM from Zero Data’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Computer Graphics

[논문리뷰] VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models

September 23, 2025

Sunghyun Cho이 [arXiv]에 게시한 ‘VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation

August 18, 2025

Junyong Noh이 [arXiv]에 게시한 ‘StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] StrandDesigner: Towards Practical Strand Generation with Sketch Guidance

August 8, 2025

Xiaobin Hu이 [arXiv]에 게시한 ‘StrandDesigner: Towards Practical Strand Generation with Sketch Guidance’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GUI Grounding

[논문리뷰] ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

September 19, 2025

Zehao Li이 [arXiv]에 게시한 ‘ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Test-Time Reinforcement Learning for GUI Grounding via Region Consistency

August 13, 2025

Zhengxi Lu이 [arXiv]에 게시한 ‘Test-Time Reinforcement Learning for GUI Grounding via Region Consistency’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization

August 11, 2025

Pengxiang Li이 [arXiv]에 게시한 ‘InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Understanding

[논문리뷰] SAIL-VL2 Technical Report

September 18, 2025

Zijian Kang이 [arXiv]에 게시한 ‘SAIL-VL2 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Can Understanding and Generation Truly Benefit Together – or Just Coexist?

September 12, 2025

Hui Han이 [arXiv]에 게시한 ‘Can Understanding and Generation Truly Benefit Together – or Just Coexist?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents

August 12, 2025

Mohit Bansal이 [arXiv]에 게시한 ‘Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Training Efficiency

[논문리뷰] OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning

September 3, 2025

Zirui Wang이 [arXiv]에 게시한 ‘OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Ovis2.5 Technical Report

August 19, 2025

Yang Li이 [arXiv]에 게시한 ‘Ovis2.5 Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents

August 12, 2025

Mohit Bansal이 [arXiv]에 게시한 ‘Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adversarial Attack

[논문리뷰] IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding

August 14, 2025

Di Zhang이 [arXiv]에 게시한 ‘IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Adversarial Video Promotion Against Text-to-Video Retrieval

August 13, 2025

Shuai Liu이 [arXiv]에 게시한 ‘Adversarial Video Promotion Against Text-to-Video Retrieval’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System

August 12, 2025

Reynold Cheng이 [arXiv]에 게시한 ‘Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mixture of Experts

[논문리뷰] Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation

September 4, 2025

Kai Li이 [arXiv]에 게시한 ‘Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation

August 12, 2025

Xiaokun Feng이 [arXiv]에 게시한 ‘Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts

August 12, 2025

Tieyuan Chen이 [arXiv]에 게시한 ‘Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sparse Attention

[논문리뷰] Mixture of Contexts for Long Video Generation

August 29, 2025

Junfei Xiao이 [arXiv]에 게시한 ‘Mixture of Contexts for Long Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Speed Always Wins: A Survey on Efficient Architectures for Large Language Models

August 19, 2025

Jusen Du이 [arXiv]에 게시한 ‘Speed Always Wins: A Survey on Efficient Architectures for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning

August 12, 2025

Baihong Yuan이 [arXiv]에 게시한 ‘Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Normalization

[논문리뷰] ΔL Normalization: Rethink Loss Aggregation in RLVR

September 10, 2025

Lili Qiu이 [arXiv]에 게시한 ‘ΔL Normalization: Rethink Loss Aggregation in RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Limitations of Normalization in Attention Mechanism

August 26, 2025

Radu State이 [arXiv]에 게시한 ‘Limitations of Normalization in Attention Mechanism’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning

August 12, 2025

Jiaheng Liu이 [arXiv]에 게시한 ‘Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vision-Language-Action (VLA) Models

[논문리뷰] A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning

September 22, 2025

Jiangmiao이 [arXiv]에 게시한 ‘A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

September 12, 2025

Zhaohui Yang이 [arXiv]에 게시한 ‘SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforcement Learning in Vision: A Survey

August 12, 2025

Qingwei Meng이 [arXiv]에 게시한 ‘Reinforcement Learning in Vision: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

ASR

[논문리뷰] WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers

September 22, 2025

Karun Kumar이 [arXiv]에 게시한 ‘WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Transcription: Mechanistic Interpretability in ASR

August 28, 2025

Aviv Shamsian이 [arXiv]에 게시한 ‘Beyond Transcription: Mechanistic Interpretability in ASR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences

August 12, 2025

Matvey Skripkin이 [arXiv]에 게시한 ‘Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-turn Dialogue

[논문리뷰] Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue

September 22, 2025

Hui Zhang이 [arXiv]에 게시한 ‘Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD

August 29, 2025

Roy Ka-Wei Lee이 [arXiv]에 게시한 ‘Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UserBench: An Interactive Gym Environment for User-Centric Agents

August 12, 2025

Jianguo Zhang이 [arXiv]에 게시한 ‘UserBench: An Interactive Gym Environment for User-Centric Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Audio-Language Models

[논문리뷰] AHELM: A Holistic Evaluation of Audio-Language Models

September 1, 2025

Siwei Yang이 [arXiv]에 게시한 ‘AHELM: A Holistic Evaluation of Audio-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence

August 20, 2025

Fernando López이 [arXiv]에 게시한 ‘MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs

August 12, 2025

Dasol Choi이 [arXiv]에 게시한 ‘When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long-Horizon Planning

[논문리뷰] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

September 12, 2025

Zhaohui Yang이 [arXiv]에 게시한 ‘SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds

August 19, 2025

Artyom Sorokin이 [arXiv]에 게시한 ‘HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL

August 13, 2025

Chuyi He이 [arXiv]에 게시한 ‘Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-view Synthesis

[논문리뷰] SPATIALGEN: Layout-guided 3D Indoor Scene Generation

September 22, 2025

Yongsen Mao이 [arXiv]에 게시한 ‘SPATIALGEN: Layout-guided 3D Indoor Scene Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation

September 1, 2025

Qi Jia이 [arXiv]에 게시한 ‘Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CharacterShot: Controllable and Consistent 4D Character Animation

August 13, 2025

Fei Shen이 [arXiv]에 게시한 ‘CharacterShot: Controllable and Consistent 4D Character Animation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Regularization

[논문리뷰] Visual Representation Alignment for Multimodal Large Language Models

September 10, 2025

Heeseong Shin이 [arXiv]에 게시한 ‘Visual Representation Alignment for Multimodal Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Metis: Training Large Language Models with Advanced Low-Bit Quantization

September 3, 2025

Hengjie Cao이 [arXiv]에 게시한 ‘Metis: Training Large Language Models with Advanced Low-Bit Quantization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition

August 13, 2025

Lukáš Burget이 [arXiv]에 게시한 ‘DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agent Evaluation

[논문리뷰] ARE: Scaling Up Agent Environments and Evaluations

September 23, 2025

Matteo Bettini이 [arXiv]에 게시한 ‘ARE: Scaling Up Agent Environments and Evaluations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers

August 21, 2025

Prathyusha Jwalapuram이 [arXiv]에 게시한 ‘MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OpenCUA: Open Foundations for Computer-Use Agents

August 13, 2025

Tianbao Xie이 [arXiv]에 게시한 ‘OpenCUA: Open Foundations for Computer-Use Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Remote Sensing

[논문리뷰] Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications

September 24, 2025

Genady Beryozkin이 [arXiv]에 게시한 ‘Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications’ 논문에 ...

[논문리뷰] FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection

September 19, 2025

Zhewei Zhang이 [arXiv]에 게시한 ‘FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion

August 13, 2025

Rachid Nedjai이 [arXiv]에 게시한 ‘WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion’ 논문에 대...

Back to Top ↑

Parallel Decoding

[논문리뷰] Set Block Decoding is a Language Model Inference Accelerator

September 8, 2025

Jeremy Reizenstein이 [arXiv]에 게시한 ‘Set Block Decoding is a Language Model Inference Accelerator’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Survey on Diffusion Language Models

August 15, 2025

Zhiqiang Shen이 [arXiv]에 게시한 ‘A Survey on Diffusion Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing

August 14, 2025

Hao Zhang이 [arXiv]에 게시한 ‘Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Distillation

[논문리뷰] Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

September 5, 2025

Lingxi Xie이 [arXiv]에 게시한 ‘Few-step Flow for 3D Generation via Marginal-Data Transport Distillation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DINOv3

August 18, 2025

Maxime Oquab이 [arXiv]에 게시한 ‘DINOv3’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing

August 14, 2025

Hao Zhang이 [arXiv]에 게시한 ‘Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Models

[논문리뷰] Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications

September 24, 2025

Genady Beryozkin이 [arXiv]에 게시한 ‘Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications’ 논문에 ...

[논문리뷰] SpotEdit: Evaluating Visually-Guided Image Editing Methods

August 26, 2025

Ersin Yumer이 [arXiv]에 게시한 ‘SpotEdit: Evaluating Visually-Guided Image Editing Methods’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation

August 14, 2025

Zhenghao Hu이 [arXiv]에 게시한 ‘Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Perception

[논문리뷰] GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning

September 23, 2025

Hou Pong Chan이 [arXiv]에 게시한 ‘GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Self-Rewarding Vision-Language Model via Reasoning Decomposition

August 28, 2025

Zhenwen Liang이 [arXiv]에 게시한 ‘Self-Rewarding Vision-Language Model via Reasoning Decomposition’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models

August 14, 2025

Zhihan Zhou이 [arXiv]에 게시한 ‘MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models’ 논문에 대한 자세한 리뷰...

Back to Top ↑

Context-Awareness

[논문리뷰] CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects

September 23, 2025

Hang Yu이 [arXiv]에 게시한 ‘CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code

September 1, 2025

Libo Chen이 [arXiv]에 게시한 ‘A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs

August 15, 2025

Yi Yuan이 [arXiv]에 게시한 ‘HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pass@k

[논문리뷰] The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward

September 12, 2025

Xiaoyu Tan이 [arXiv]에 게시한 ‘The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward’ 논문에 대한...

[논문리뷰] Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

August 25, 2025

Ying Nian Wu이 [arXiv]에 게시한 ‘Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models

August 15, 2025

Qinghao Ye이 [arXiv]에 게시한 ‘Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sim-to-Real Transfer

[논문리뷰] WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning

September 17, 2025

Huifeng Yin이 [arXiv]에 게시한 ‘WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

September 12, 2025

Zhaohui Yang이 [arXiv]에 게시한 ‘SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SSRL: Self-Search Reinforcement Learning

August 18, 2025

Yanxu Chen이 [arXiv]에 게시한 ‘SSRL: Self-Search Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Synthesis

[논문리뷰] Lynx: Towards High-Fidelity Personalized Video Generation

September 22, 2025

Linjie Luo이 [arXiv]에 게시한 ‘Lynx: Towards High-Fidelity Personalized Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mixture of Contexts for Long Video Generation

August 29, 2025

Junfei Xiao이 [arXiv]에 게시한 ‘Mixture of Contexts for Long Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 4DNeX: Feed-Forward 4D Generative Modeling Made Easy

August 19, 2025

Zeng Tao이 [arXiv]에 게시한 ‘4DNeX: Feed-Forward 4D Generative Modeling Made Easy’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Controllable Generation

[논문리뷰] X-Part: high fidelity and structure coherent shape decomposition

September 15, 2025

Yunhan Yang이 [arXiv]에 게시한 ‘X-Part: high fidelity and structure coherent shape decomposition’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation

September 4, 2025

Kai Li이 [arXiv]에 게시한 ‘Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforcement Learning with Rubric Anchors

August 19, 2025

Haokai Xu이 [arXiv]에 게시한 ‘Reinforcement Learning with Rubric Anchors’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Supervised Learning

[논문리뷰] Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR

September 3, 2025

Lu Wang이 [arXiv]에 게시한 ‘Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels

August 27, 2025

Dinesh Jayaraman이 [arXiv]에 게시한 ‘Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Advances in Speech Separation: Techniques, Challenges, and Future Trends

August 20, 2025

Zhuo Chen이 [arXiv]에 게시한 ‘Advances in Speech Separation: Techniques, Challenges, and Future Trends’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Tool-Integrated Reasoning

[논문리뷰] THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning

September 18, 2025

Yicheng Pan이 [arXiv]에 게시한 ‘THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning

September 3, 2025

Qian Liu이 [arXiv]에 게시한 ‘SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

August 20, 2025

Liam-Liu이 [arXiv]에 게시한 ‘Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Calibration

[논문리뷰] Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs

September 19, 2025

Katharina von der Wense이 [arXiv]에 게시한 ‘Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Why Language Models Hallucinate

September 8, 2025

Edwin Zhang이 [arXiv]에 게시한 ‘Why Language Models Hallucinate’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation

August 20, 2025

Xinyi Wang이 [arXiv]에 게시한 ‘Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Quantization

[논문리뷰] Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs

September 17, 2025

Luca Benini이 [arXiv]에 게시한 ‘Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling

September 10, 2025

Diana Marculescu이 [arXiv]에 게시한 ‘Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Semantic IDs for Joint Generative Search and Recommendation

August 20, 2025

Enrico Palumbo이 [arXiv]에 게시한 ‘Semantic IDs for Joint Generative Search and Recommendation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adaptive Sampling

[논문리뷰] From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token’s Nature

September 23, 2025

Bin Cui이 [arXiv]에 게시한 ‘From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token’s Nature’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Single-stream Policy Optimization

September 17, 2025

Zihan Ding이 [arXiv]에 게시한 ‘Single-stream Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Deep Think with Confidence

August 22, 2025

Xuewei Wang이 [arXiv]에 게시한 ‘Deep Think with Confidence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Process Reward Models

[논문리뷰] SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning

September 23, 2025

Zhaopeng Tu이 [arXiv]에 게시한 ‘SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] StepWiser: Stepwise Generative Judges for Wiser Reasoning

August 28, 2025

Olga Golovneva이 [arXiv]에 게시한 ‘StepWiser: Stepwise Generative Judges for Wiser Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models

August 22, 2025

Lifan Guo이 [arXiv]에 게시한 ‘Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Financial Reasoning

[논문리뷰] FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning

September 19, 2025

Jiashuo Liu이 [arXiv]에 게시한 ‘FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading

September 15, 2025

Chenyu You이 [arXiv]에 게시한 ‘QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models

August 22, 2025

Lifan Guo이 [arXiv]에 게시한 ‘Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Scene Generation

[논문리뷰] VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models

September 23, 2025

Sunghyun Cho이 [arXiv]에 게시한 ‘VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SPATIALGEN: Layout-guided 3D Indoor Scene Generation

September 22, 2025

Yongsen Mao이 [arXiv]에 게시한 ‘SPATIALGEN: Layout-guided 3D Indoor Scene Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass

August 22, 2025

Ya Zhang이 [arXiv]에 게시한 ‘SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-to-Video

[논문리뷰] HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

September 12, 2025

Zhuowei Chen이 [arXiv]에 게시한 ‘HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RewardDance: Reward Scaling in Visual Generation

September 11, 2025

Liang Li이 [arXiv]에 게시한 ‘RewardDance: Reward Scaling in Visual Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Waver: Wave Your Way to Lifelike Video Generation

August 22, 2025

Yifu Zhang이 [arXiv]에 게시한 ‘Waver: Wave Your Way to Lifelike Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image-to-Video

[논문리뷰] ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment

September 23, 2025

Yue Ma이 [arXiv]에 게시한 ‘ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

September 12, 2025

Zhuowei Chen이 [arXiv]에 게시한 ‘HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Waver: Wave Your Way to Lifelike Video Generation

August 22, 2025

Yifu Zhang이 [arXiv]에 게시한 ‘Waver: Wave Your Way to Lifelike Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long Video Understanding

[논문리뷰] Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding

September 5, 2025

Lionel Ni이 [arXiv]에 게시한 ‘Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding

September 3, 2025

Xuanyu Zheng이 [arXiv]에 게시한 ‘ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding

August 22, 2025

Rui Guo이 [arXiv]에 게시한 ‘When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human Motion Synthesis

[논문리뷰] MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment

August 28, 2025

An-An Liu이 [arXiv]에 게시한 ‘MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation

August 27, 2025

Jiaqi Yang이 [arXiv]에 게시한 ‘OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EgoTwin: Dreaming Body and View in First Person

August 25, 2025

Wentao Wang이 [arXiv]에 게시한 ‘EgoTwin: Dreaming Body and View in First Person’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Generation

[논문리뷰] Can Understanding and Generation Truly Benefit Together – or Just Coexist?

September 12, 2025

Hui Han이 [arXiv]에 게시한 ‘Can Understanding and Generation Truly Benefit Together – or Just Coexist?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation

August 28, 2025

Yan Zhou이 [arXiv]에 게시한 ‘MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EgoTwin: Dreaming Body and View in First Person

August 25, 2025

Wentao Wang이 [arXiv]에 게시한 ‘EgoTwin: Dreaming Body and View in First Person’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scientific Reasoning

[논문리뷰] Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning

August 27, 2025

Arman Cohan이 [arXiv]에 게시한 ‘Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics

August 27, 2025

Dongchen Huang이 [arXiv]에 게시한 ‘CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation

August 26, 2025

Xihui Liu이 [arXiv]에 게시한 ‘T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hallucinations

[논문리뷰] Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet

September 9, 2025

See-Kiong Ng이 [arXiv]에 게시한 ‘Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Self-Rewarding Vision-Language Model via Reasoning Decomposition

August 28, 2025

Zhenwen Liang이 [arXiv]에 게시한 ‘Self-Rewarding Vision-Language Model via Reasoning Decomposition’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Transcription: Mechanistic Interpretability in ASR

August 28, 2025

Aviv Shamsian이 [arXiv]에 게시한 ‘Beyond Transcription: Mechanistic Interpretability in ASR’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Generation

[논문리뷰] Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

September 5, 2025

Lingxi Xie이 [arXiv]에 게시한 ‘Few-step Flow for 3D Generation via Marginal-Data Transport Distillation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation

September 1, 2025

Qi Jia이 [arXiv]에 게시한 ‘Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Collaborative Multi-Modal Coding for High-Quality 3D Generation

August 29, 2025

Ziwei Liu이 [arXiv]에 게시한 ‘Collaborative Multi-Modal Coding for High-Quality 3D Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Diversity

[논문리뷰] Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation

September 3, 2025

Xiaolei Huang이 [arXiv]에 게시한 ‘Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation’ 논문에 대한 자...

[논문리뷰] TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis

September 1, 2025

Pengcheng Chen이 [arXiv]에 게시한 ‘TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning

August 29, 2025

Simin Ma이 [arXiv]에 게시한 ‘TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Unified Framework

[논문리뷰] Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

September 22, 2025

Wenyu Wang이 [arXiv]에 게시한 ‘Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Towards a Unified View of Large Language Model Post-Training

September 5, 2025

Hongyi Liu이 [arXiv]에 게시한 ‘Towards a Unified View of Large Language Model Post-Training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning

August 29, 2025

Jiahe Tian이 [arXiv]에 게시한 ‘USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Synthetic Data Generation

[논문리뷰] Towards General Agentic Intelligence via Environment Scaling

September 17, 2025

Guangyu Li이 [arXiv]에 게시한 ‘Towards General Agentic Intelligence via Environment Scaling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem

September 9, 2025

Damien Sileo이 [arXiv]에 게시한 ‘Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation

September 3, 2025

Xiaolei Huang이 [arXiv]에 게시한 ‘Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation’ 논문에 대한 자...

Back to Top ↑

Post-training

[논문리뷰] Reconstruction Alignment Improves Unified Multimodal Models

September 10, 2025

XuDong Wang이 [arXiv]에 게시한 ‘Reconstruction Alignment Improves Unified Multimodal Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Why Language Models Hallucinate

September 8, 2025

Edwin Zhang이 [arXiv]에 게시한 ‘Why Language Models Hallucinate’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Jointly Reinforcing Diversity and Quality in Language Model Generations

September 3, 2025

Tianlu이 [arXiv]에 게시한 ‘Jointly Reinforcing Diversity and Quality in Language Model Generations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Deep Research

[논문리뷰] WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents

September 17, 2025

Wenbiao Yin이 [arXiv]에 게시한 ‘WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Open Data Synthesis For Deep Research

September 4, 2025

Zheng Liu이 [arXiv]에 게시한 ‘Open Data Synthesis For Deep Research’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Universal Deep Research: Bring Your Own Model and Strategy

September 3, 2025

Pavlo Molchanov이 [arXiv]에 게시한 ‘Universal Deep Research: Bring Your Own Model and Strategy’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Docker

[논문리뷰] Training Language Model Agents to Find Vulnerabilities with CTF-Dojo

August 27, 2025

Zijian Wang이 [arXiv]에 게시한 ‘Training Language Model Agents to Find Vulnerabilities with CTF-Dojo’ 논문에 대한 자세한 리뷰입니다.

[Docker] 빠른 빌드 방법

February 14, 2025

Docker 빌드 속도를 높이는 방법을 공유합니다.

Back to Top ↑

Ambiguity Resolution

[논문리뷰] Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue

September 22, 2025

Hui Zhang이 [arXiv]에 게시한 ‘Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations

August 3, 2025

Yiwen Guo이 [arXiv]에 게시한 ‘C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Machine Unlearning

[논문리뷰] Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning

September 18, 2025

Zhou Yang이 [arXiv]에 게시한 ‘Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Efficient Machine Unlearning via Influence Approximation

August 3, 2025

Enhong Chen이 [arXiv]에 게시한 ‘Efficient Machine Unlearning via Influence Approximation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Editing

[논문리뷰] SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation

September 16, 2025

Heshaam Faili이 [arXiv]에 게시한 ‘SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Efficient Machine Unlearning via Influence Approximation

August 3, 2025

Enhong Chen이 [arXiv]에 게시한 ‘Efficient Machine Unlearning via Influence Approximation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Arabic NLP

[논문리뷰] Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale

September 18, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Enhanced Arabic Text Retrieval with Attentive Relevance Scoring

August 3, 2025

Abdenour Hadid이 [arXiv]에 게시한 ‘Enhanced Arabic Text Retrieval with Attentive Relevance Scoring’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

NeRF

[논문리뷰] Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research

August 20, 2025

Susanne Schmidt이 [arXiv]에 게시한 ‘Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NeRF Is a Valuable Assistant for 3D Gaussian Splatting

August 3, 2025

ZeSheng Wang이 [arXiv]에 게시한 ‘NeRF Is a Valuable Assistant for 3D Gaussian Splatting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hybrid Model

[논문리뷰] GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing

August 11, 2025

Przemysław Spurek이 [arXiv]에 게시한 ‘GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NeRF Is a Valuable Assistant for 3D Gaussian Splatting

August 3, 2025

ZeSheng Wang이 [arXiv]에 게시한 ‘NeRF Is a Valuable Assistant for 3D Gaussian Splatting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scene Representation

[논문리뷰] VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

September 24, 2025

Haoxiao Wang이 [arXiv]에 게시한 ‘VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NeRF Is a Valuable Assistant for 3D Gaussian Splatting

August 3, 2025

ZeSheng Wang이 [arXiv]에 게시한 ‘NeRF Is a Valuable Assistant for 3D Gaussian Splatting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sparse View

[논문리뷰] Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds

August 22, 2025

Chuiyun Wu이 [arXiv]에 게시한 ‘Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NeRF Is a Valuable Assistant for 3D Gaussian Splatting

August 3, 2025

ZeSheng Wang이 [arXiv]에 게시한 ‘NeRF Is a Valuable Assistant for 3D Gaussian Splatting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Linear Attention

[논문리뷰] Speed Always Wins: A Survey on Efficient Architectures for Large Language Models

August 19, 2025

Jusen Du이 [arXiv]에 게시한 ‘Speed Always Wins: A Survey on Efficient Architectures for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective

August 3, 2025

Eric C. Larson이 [arXiv]에 게시한 ‘On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Transformer Architectures

[논문리뷰] Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling

August 26, 2025

Daniil Orel이 [arXiv]에 게시한 ‘Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective

August 3, 2025

Eric C. Larson이 [arXiv]에 게시한 ‘On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Perception

[논문리뷰] UItron: Foundational GUI Agent with Advanced Perception and Planning

September 1, 2025

Yufeng Zhong이 [arXiv]에 게시한 ‘UItron: Foundational GUI Agent with Advanced Perception and Planning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Phi-Ground Tech Report: Advancing Perception in GUI Grounding

August 3, 2025

Kai Qiu이 [arXiv]에 게시한 ‘Phi-Ground Tech Report: Advancing Perception in GUI Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Direct Preference Optimization

[논문리뷰] Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report

August 5, 2025

Anu Vellore이 [arXiv]에 게시한 ‘Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Phi-Ground Tech Report: Advancing Perception in GUI Grounding

August 3, 2025

Kai Qiu이 [arXiv]에 게시한 ‘Phi-Ground Tech Report: Advancing Perception in GUI Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Formal Verification

[논문리뷰] Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction

August 6, 2025

Jui-Hui Chung이 [arXiv]에 게시한 ‘Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving

August 3, 2025

Zhicheng Jiang이 [arXiv]에 게시한 ‘Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Lean

[논문리뷰] Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction

August 6, 2025

Jui-Hui Chung이 [arXiv]에 게시한 ‘Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving

August 3, 2025

Zhicheng Jiang이 [arXiv]에 게시한 ‘Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-view Learning

[논문리뷰] 3D Aware Region Prompted Vision Language Model

September 17, 2025

Xiaolong Li이 [arXiv]에 게시한 ‘3D Aware Region Prompted Vision Language Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] iLRM: An Iterative Large 3D Reconstruction Model

August 3, 2025

Abdelrahman Mohamed이 [arXiv]에 게시한 ‘iLRM: An Iterative Large 3D Reconstruction Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pre-training

[논문리뷰] Reinforcement Learning on Pre-Training Data

September 24, 2025

Evander Yang이 [arXiv]에 게시한 ‘Reinforcement Learning on Pre-Training Data’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models

August 3, 2025

Kaixin Wang이 [arXiv]에 게시한 ‘villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Inference Optimization

[논문리뷰] A Survey on Diffusion Language Models

August 15, 2025

Zhiqiang Shen이 [arXiv]에 게시한 ‘A Survey on Diffusion Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models

August 4, 2025

Jiaqi Wang이 [arXiv]에 게시한 ‘Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Gaussian Splatting (3DGS)

[논문리뷰] HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis

September 24, 2025

Dan Xu이 [arXiv]에 게시한 ‘HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation

August 4, 2025

Jianjiang Feng이 [arXiv]에 게시한 ‘IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Conversational AI

[논문리뷰] OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models

August 29, 2025

Alex Endert이 [arXiv]에 게시한 ‘OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Investigating Hallucination in Conversations for Low Resource Languages

August 4, 2025

Fatemeh Jamshidi이 [arXiv]에 게시한 ‘Investigating Hallucination in Conversations for Low Resource Languages’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Segmentation

[논문리뷰] Autoregressive Universal Video Segmentation Model

August 27, 2025

Albert Gu이 [arXiv]에 게시한 ‘Autoregressive Universal Video Segmentation Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Multimodal Referring Segmentation: A Survey

August 4, 2025

Zuxuan Wu이 [arXiv]에 게시한 ‘Multimodal Referring Segmentation: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

End-to-End Learning

[논문리뷰] Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

August 20, 2025

Liam-Liu이 [arXiv]에 게시한 ‘Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PixNerd: Pixel Neural Field Diffusion

August 4, 2025

Limin Wang이 [arXiv]에 게시한 ‘PixNerd: Pixel Neural Field Diffusion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Test-time Scaling

[논문리뷰] What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT

September 24, 2025

Anthony Hartshorn이 [arXiv]에 게시한 ‘What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks

August 5, 2025

Zhiwei Zhang이 [arXiv]에 게시한 ‘AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Resource Allocation

[논문리뷰] Virtual Agent Economies

September 15, 2025

William A. Cunningham이 [arXiv]에 게시한 ‘Virtual Agent Economies’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks

August 5, 2025

Zhiwei Zhang이 [arXiv]에 게시한 ‘AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Training

[논문리뷰] TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training

September 1, 2025

Jiyao Deng이 [arXiv]에 게시한 ‘TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Cyber-Zero: Training Cybersecurity Agents without Runtime

August 5, 2025

Zijian Wang이 [arXiv]에 게시한 ‘Cyber-Zero: Training Cybersecurity Agents without Runtime’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

CTF Challenges

[논문리뷰] Training Language Model Agents to Find Vulnerabilities with CTF-Dojo

August 27, 2025

Zijian Wang이 [arXiv]에 게시한 ‘Training Language Model Agents to Find Vulnerabilities with CTF-Dojo’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Cyber-Zero: Training Cybersecurity Agents without Runtime

August 5, 2025

Zijian Wang이 [arXiv]에 게시한 ‘Cyber-Zero: Training Cybersecurity Agents without Runtime’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vision-Language-Action (VLA)

[논문리뷰] Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies

August 28, 2025

Sitong Mao이 [arXiv]에 게시한 ‘Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation

August 5, 2025

Yang Tian이 [arXiv]에 게시한 ‘InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cybersecurity

[논문리뷰] Training Language Model Agents to Find Vulnerabilities with CTF-Dojo

August 27, 2025

Zijian Wang이 [arXiv]에 게시한 ‘Training Language Model Agents to Find Vulnerabilities with CTF-Dojo’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report

August 5, 2025

Anu Vellore이 [arXiv]에 게시한 ‘Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

DPO

[논문리뷰] ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding

September 3, 2025

Xuanyu Zheng이 [arXiv]에 게시한 ‘ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Personalized Safety Alignment for Text-to-Image Diffusion Models

August 5, 2025

Kaidong Yu이 [arXiv]에 게시한 ‘Personalized Safety Alignment for Text-to-Image Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Content Moderation

[논문리뷰] D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning

September 9, 2025

Dhanvin Sanjay Namboodiri이 [arXiv]에 게시한 ‘D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Personalized Safety Alignment for Text-to-Image Diffusion Models

August 5, 2025

Kaidong Yu이 [arXiv]에 게시한 ‘Personalized Safety Alignment for Text-to-Image Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Brain-inspired AI

[논문리뷰] From reactive to cognitive: brain-inspired spatial intelligence for embodied agents

September 2, 2025

Songming Liu이 [arXiv]에 게시한 ‘From reactive to cognitive: brain-inspired spatial intelligence for embodied agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Lifelong Learning in Physical Embodied Systems

August 5, 2025

Junkun Hong이 [arXiv]에 게시한 ‘RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Lifelong Learning in Physical Embodied Systems’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dense Retrieval

[논문리뷰] MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction

September 23, 2025

Xintao Chen이 [arXiv]에 게시한 ‘MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension

August 5, 2025

Liyan Xu이 [arXiv]에 게시한 ‘SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

RAG

[논문리뷰] PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts

August 15, 2025

Rui Lu이 [arXiv]에 게시한 ‘PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension

August 5, 2025

Liyan Xu이 [arXiv]에 게시한 ‘SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Parameter-Efficient Learning

[논문리뷰] QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models

September 23, 2025

Jae-Joon Kim이 [arXiv]에 게시한 ‘QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization

August 6, 2025

Aman Chadha이 [arXiv]에 게시한 ‘AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization...

Back to Top ↑

Visual Language Models

[논문리뷰] Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search

September 10, 2025

Tianjian Li이 [arXiv]에 게시한 ‘Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ChartCap: Mitigating Hallucination of Dense Chart Captioning

August 6, 2025

Gunhee Kim이 [arXiv]에 게시한 ‘ChartCap: Mitigating Hallucination of Dense Chart Captioning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Visualization

[논문리뷰] CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media

September 16, 2025

Subasish Das이 [arXiv]에 게시한 ‘CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ChartCap: Mitigating Hallucination of Dense Chart Captioning

August 6, 2025

Gunhee Kim이 [arXiv]에 게시한 ‘ChartCap: Mitigating Hallucination of Dense Chart Captioning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hallucination Detection

[논문리뷰] Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

September 23, 2025

Fatma Betül Terzioğlu이 [arXiv]에 게시한 ‘Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward

August 6, 2025

Songyang Gao이 [arXiv]에 게시한 ‘CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Zero-Shot Generalization

[논문리뷰] Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels

August 27, 2025

Dinesh Jayaraman이 [arXiv]에 게시한 ‘Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer

August 6, 2025

Shunyu Yao이 [arXiv]에 게시한 ‘LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Agent

[논문리뷰] Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System

August 12, 2025

Reynold Cheng이 [arXiv]에 게시한 ‘Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?

August 6, 2025

Yaojie Lu이 [arXiv]에 게시한 ‘LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Quality

[논문리뷰] Interleaving Reasoning for Better Text-to-Image Generation

September 9, 2025

Shixiang Tang이 [arXiv]에 게시한 ‘Interleaving Reasoning for Better Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation

August 6, 2025

Chenyang Si이 [arXiv]에 게시한 ‘LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Autoregressive Generation

[논문리뷰] Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing

August 14, 2025

Hao Zhang이 [arXiv]에 게시한 ‘Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation

August 6, 2025

Chenyang Si이 [arXiv]에 게시한 ‘LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pose Control

[논문리뷰] CharacterShot: Controllable and Consistent 4D Character Animation

August 13, 2025

Fei Shen이 [arXiv]에 게시한 ‘CharacterShot: Controllable and Consistent 4D Character Animation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Multi-human Interactive Talking Dataset

August 6, 2025

Mike Zheng Shou이 [arXiv]에 게시한 ‘Multi-human Interactive Talking Dataset’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Discrete Diffusion

[논문리뷰] Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies

August 28, 2025

Sitong Mao이 [arXiv]에 게시한 ‘Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

August 6, 2025

Fan Xia이 [arXiv]에 게시한 ‘Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Understanding

[논문리뷰] Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation

September 19, 2025

Xihui Liu이 [arXiv]에 게시한 ‘Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation

August 6, 2025

Tianyidan Xie이 [arXiv]에 게시한 ‘Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Unified Architecture

[논문리뷰] MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

September 22, 2025

jialingt이 [arXiv]에 게시한 ‘MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation

August 6, 2025

Tianyidan Xie이 [arXiv]에 게시한 ‘Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Natural Language Understanding

[논문리뷰] The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang

September 3, 2025

Solomon Tsai이 [arXiv]에 게시한 ‘The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding

August 7, 2025

Jianke Zhu이 [arXiv]에 게시한 ‘A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Autonomous Driving

[논문리뷰] 3D and 4D World Modeling: A Survey

September 11, 2025

Ao Liang이 [arXiv]에 게시한 ‘3D and 4D World Modeling: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding

August 7, 2025

Jianke Zhu이 [arXiv]에 게시한 ‘A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agent Frameworks

[논문리뷰] RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation

September 22, 2025

Steven Liu이 [arXiv]에 게시한 ‘RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Efficient Agents: Building Effective Agents While Reducing Cost

August 7, 2025

Yue Hou이 [arXiv]에 게시한 ‘Efficient Agents: Building Effective Agents While Reducing Cost’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Optimization

[논문리뷰] TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training

September 1, 2025

Jiyao Deng이 [arXiv]에 게시한 ‘TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Efficient Agents: Building Effective Agents While Reducing Cost

August 7, 2025

Yue Hou이 [arXiv]에 게시한 ‘Efficient Agents: Building Effective Agents While Reducing Cost’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Resource Management

[논문리뷰] Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference

August 28, 2025

Chunlei Han이 [arXiv]에 게시한 ‘Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Efficient Agents: Building Effective Agents While Reducing Cost

August 7, 2025

Yue Hou이 [arXiv]에 게시한 ‘Efficient Agents: Building Effective Agents While Reducing Cost’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Actor-Critic

[논문리뷰] Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR

September 3, 2025

Lu Wang이 [arXiv]에 게시한 ‘Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success

August 7, 2025

Ruslan Rakhimov이 [arXiv]에 게시한 ‘Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success’ 논문에 대한 자세한 리뷰...

Back to Top ↑

4D Generation

[논문리뷰] 4DNeX: Feed-Forward 4D Generative Modeling Made Easy

August 19, 2025

Zeng Tao이 [arXiv]에 게시한 ‘4DNeX: Feed-Forward 4D Generative Modeling Made Easy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

August 7, 2025

Feng Zhao이 [arXiv]에 게시한 ‘Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Instance Segmentation

[논문리뷰] RynnEC: Bringing MLLMs into Embodied World

August 21, 2025

jiangpinliu이 [arXiv]에 게시한 ‘RynnEC: Bringing MLLMs into Embodied World’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IAUNet: Instance-Aware U-Net

August 7, 2025

Dmytro Fishman이 [arXiv]에 게시한 ‘IAUNet: Instance-Aware U-Net’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

U-Net

[논문리뷰] IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding

August 14, 2025

Di Zhang이 [arXiv]에 게시한 ‘IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IAUNet: Instance-Aware U-Net

August 7, 2025

Dmytro Fishman이 [arXiv]에 게시한 ‘IAUNet: Instance-Aware U-Net’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Flywheel

[논문리뷰] UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

September 3, 2025

Haoyang Zou이 [arXiv]에 게시한 ‘UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards

August 7, 2025

Ling-I Wu이 [arXiv]에 게시한 ‘IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

UI Automation

[논문리뷰] Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents

August 28, 2025

Yue Yao이 [arXiv]에 게시한 ‘Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LaTCoder: Converting Webpage Design to Code with Layout-as-Thought

August 7, 2025

Tianpeng Lv이 [arXiv]에 게시한 ‘LaTCoder: Converting Webpage Design to Code with Layout-as-Thought’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Pruning

[논문리뷰] GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings

September 16, 2025

Yixuan Tang이 [arXiv]에 게시한 ‘GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LeanK: Learnable K Cache Channel Pruning for Efficient Decoding

August 7, 2025

Yuqing Yang이 [arXiv]에 게시한 ‘LeanK: Learnable K Cache Channel Pruning for Efficient Decoding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Memory Optimization

[논문리뷰] MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs

August 12, 2025

Jianguo Li이 [arXiv]에 게시한 ‘MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LeanK: Learnable K Cache Channel Pruning for Efficient Decoding

August 7, 2025

Yuqing Yang이 [arXiv]에 게시한 ‘LeanK: Learnable K Cache Channel Pruning for Efficient Decoding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Audio Understanding

[논문리뷰] Qwen3-Omni Technical Report

September 23, 2025

Lhma-aslp이 [arXiv]에 게시한 ‘Qwen3-Omni Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MiDashengLM: Efficient Audio Understanding with General Audio Captions

August 7, 2025

Yadong Niu이 [arXiv]에 게시한 ‘MiDashengLM: Efficient Audio Understanding with General Audio Captions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodality

[논문리뷰] AHELM: A Holistic Evaluation of Audio-Language Models

September 1, 2025

Siwei Yang이 [arXiv]에 게시한 ‘AHELM: A Holistic Evaluation of Audio-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MiDashengLM: Efficient Audio Understanding with General Audio Captions

August 7, 2025

Yadong Niu이 [arXiv]에 게시한 ‘MiDashengLM: Efficient Audio Understanding with General Audio Captions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Peer Review

[논문리뷰] aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists

August 22, 2025

Heng Zhang이 [arXiv]에 게시한 ‘aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference

August 7, 2025

Jiaying Wu이 [arXiv]에 게시한 ‘Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Out-of-Distribution

[논문리뷰] Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?

September 5, 2025

Yu Fu이 [arXiv]에 게시한 ‘Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization

August 7, 2025

Kechi Zhang이 [arXiv]에 게시한 ‘RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization’ 논문에 대한 자세한 리뷰입...

Back to Top ↑

Computer Use Agent

[논문리뷰] CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

August 28, 2025

Jianze Liang이 [arXiv]에 게시한 ‘CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning’ 논문에 대한 ...

[논문리뷰] SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience

August 7, 2025

Xiaoyi Dong이 [arXiv]에 게시한 ‘SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-to-3D Generation

[논문리뷰] MV-RAG: Retrieval Augmented Multiview Diffusion

August 26, 2025

sagiebenaim이 [arXiv]에 게시한 ‘MV-RAG: Retrieval Augmented Multiview Diffusion’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Sel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generation

August 7, 2025

Hao Huang이 [arXiv]에 게시한 ‘Sel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-modal Large Language Models

[논문리뷰] RynnEC: Bringing MLLMs into Embodied World

August 21, 2025

jiangpinliu이 [arXiv]에 게시한 ‘RynnEC: Bringing MLLMs into Embodied World’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Sel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generation

August 7, 2025

Hao Huang이 [arXiv]에 게시한 ‘Sel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-to-Audio

[논문리뷰] AudioStory: Generating Long-Form Narrative Audio with Large Language Models

August 28, 2025

Yixiao Ge이 [arXiv]에 게시한 ‘AudioStory: Generating Long-Form Narrative Audio with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering

August 7, 2025

Ambuj Mehrish이 [arXiv]에 게시한 ‘SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Turn Interaction

[논문리뷰] AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning

September 11, 2025

Honglin Guo이 [arXiv]에 게시한 ‘AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning

August 7, 2025

Maksim Nekrashevich이 [arXiv]에 게시한 ‘Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cognitive Reasoning

[논문리뷰] MovieCORE: COgnitive REasoning in Movies

August 27, 2025

Hung-Ting Su이 [arXiv]에 게시한 ‘MovieCORE: COgnitive REasoning in Movies’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents

August 7, 2025

Xinyu Yang이 [arXiv]에 게시한 ‘Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Benchmark Evaluation

[논문리뷰] Has GPT-5 Achieved Spatial Intelligence? An Empirical Study

August 19, 2025

Ruisi Wang이 [arXiv]에 게시한 ‘Has GPT-5 Achieved Spatial Intelligence? An Empirical Study’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?

August 8, 2025

Junjie Yang이 [arXiv]에 게시한 ‘Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Document Understanding

[논문리뷰] Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR

September 24, 2025

Zeina Aldallal이 [arXiv]에 게시한 ‘Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?

August 8, 2025

Junjie Yang이 [arXiv]에 게시한 ‘Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Large Multimodal Models

[논문리뷰] Morae: Proactively Pausing UI Agents for User Choices

September 1, 2025

Amy Pavel이 [arXiv]에 게시한 ‘Morae: Proactively Pausing UI Agents for User Choices’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability

August 8, 2025

Yuan Wu이 [arXiv]에 게시한 ‘Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability’ 논문에 대...

Back to Top ↑

Evaluation Framework

[논문리뷰] VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions

September 15, 2025

Dong Zhang이 [arXiv]에 게시한 ‘VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability

August 8, 2025

Yuan Wu이 [arXiv]에 게시한 ‘Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability’ 논문에 대...

Back to Top ↑

Action Planning

[논문리뷰] BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent

September 22, 2025

Jiahui Yang이 [arXiv]에 게시한 ‘BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning

August 8, 2025

Ziming Wang이 [arXiv]에 게시한 ‘DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Efficiency

[논문리뷰] A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models

August 20, 2025

Zishang Jiang이 [arXiv]에 게시한 ‘A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Don’t Overthink It: A Survey of Efficient R1-style Large Reasoning Models

August 8, 2025

Fangzhou Yao이 [arXiv]에 게시한 ‘Don’t Overthink It: A Survey of Efficient R1-style Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

World Model

[논문리뷰] Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model

August 19, 2025

Yifan Zhang이 [arXiv]에 게시한 ‘Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation

August 8, 2025

Shengcong Chen이 [arXiv]에 게시한 ‘Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Robotics Simulation

[논문리뷰] CAMAR: Continuous Actions Multi-Agent Routing

August 20, 2025

Alexey Skrynnik이 [arXiv]에 게시한 ‘CAMAR: Continuous Actions Multi-Agent Routing’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation

August 8, 2025

Shengcong Chen이 [arXiv]에 게시한 ‘Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human Evaluation

[논문리뷰] DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultural Text Adaptation in Indian Context

September 23, 2025

Maunendra Sankar Desarkar이 [arXiv]에 게시한 ‘DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultur...

[논문리뷰] Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis

August 8, 2025

Reshmi Ghosh이 [arXiv]에 게시한 ‘Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Overthinking

[논문리뷰] Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information

August 19, 2025

Xi Yang이 [arXiv]에 게시한 ‘Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis

August 8, 2025

Reshmi Ghosh이 [arXiv]에 게시한 ‘Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Iterative Reasoning

[논문리뷰] WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents

September 17, 2025

Wenbiao Yin이 [arXiv]에 게시한 ‘WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking

August 8, 2025

Chao Wang이 [arXiv]에 게시한 ‘I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sociolinguistics

[논문리뷰] Large Language Models Discriminate Against Speakers of German Dialects

September 24, 2025

Katharina von der Wense이 [arXiv]에 게시한 ‘Large Language Models Discriminate Against Speakers of German Dialects’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations

August 8, 2025

Chirag Shah이 [arXiv]에 게시한 ‘I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations’ 논문에...

Back to Top ↑

Model Evaluation

[논문리뷰] What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT

September 24, 2025

Anthony Hartshorn이 [arXiv]에 게시한 ‘What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction

August 8, 2025

Prajit Das이 [arXiv]에 게시한 ‘PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Label-Free Learning

[논문리뷰] When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs

September 23, 2025

Anand Mishra이 [arXiv]에 게시한 ‘When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs’ 논문에...

[논문리뷰] Adapting Vision-Language Models Without Labels: A Comprehensive Survey

August 11, 2025

Eleni Chatzi이 [arXiv]에 게시한 ‘Adapting Vision-Language Models Without Labels: A Comprehensive Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Neural Radiance Fields (NeRF)

[논문리뷰] HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis

September 24, 2025

Dan Xu이 [arXiv]에 게시한 ‘HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing

August 11, 2025

Przemysław Spurek이 [arXiv]에 게시한 ‘GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Interactive Editing

[논문리뷰] X-Part: high fidelity and structure coherent shape decomposition

September 15, 2025

Yunhan Yang이 [arXiv]에 게시한 ‘X-Part: high fidelity and structure coherent shape decomposition’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing

August 11, 2025

Przemysław Spurek이 [arXiv]에 게시한 ‘GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-time Rendering

[논문리뷰] HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis

September 24, 2025

Dan Xu이 [arXiv]에 게시한 ‘HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing

August 11, 2025

Przemysław Spurek이 [arXiv]에 게시한 ‘GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semantic Alignment

[논문리뷰] 2D Gaussian Splatting with Semantic Alignment for Image Inpainting

September 12, 2025

Guangming Lu이 [arXiv]에 게시한 ‘2D Gaussian Splatting with Semantic Alignment for Image Inpainting’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization

August 11, 2025

Pengxiang Li이 [arXiv]에 게시한 ‘InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Scene Reconstruction

[논문리뷰] Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

September 24, 2025

Yifeng Jiang이 [arXiv]에 게시한 ‘Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LightSwitch: Multi-view Relighting with Material-guided Diffusion

August 11, 2025

Shubham Tulsiani이 [arXiv]에 게시한 ‘LightSwitch: Multi-view Relighting with Material-guided Diffusion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Memory Management

[논문리뷰] Mixture of Contexts for Long Video Generation

August 29, 2025

Junfei Xiao이 [arXiv]에 게시한 ‘Mixture of Contexts for Long Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Memp: Exploring Agent Procedural Memory

August 11, 2025

Shuofei Qiao이 [arXiv]에 게시한 ‘Memp: Exploring Agent Procedural Memory’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Mesh Generation

[논문리뷰] FastMesh:Efficient Artistic Mesh Generation via Component Decoupling

August 27, 2025

Xingang Pan이 [arXiv]에 게시한 ‘FastMesh:Efficient Artistic Mesh Generation via Component Decoupling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh

August 11, 2025

Yi Yang이 [arXiv]에 게시한 ‘MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-to-3D

[논문리뷰] Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation

September 1, 2025

Qi Jia이 [arXiv]에 게시한 ‘Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh

August 11, 2025

Yi Yang이 [arXiv]에 게시한 ‘MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Code Reasoning

[논문리뷰] AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions

August 25, 2025

Yidi Du이 [arXiv]에 게시한 ‘AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal

August 11, 2025

Chengcheng Wan이 [arXiv]에 게시한 ‘Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

CoT Compression

[논문리뷰] Compressing Chain-of-Thought in LLMs via Step Entropy

August 12, 2025

Zhijian Xu이 [arXiv]에 게시한 ‘Compressing Chain-of-Thought in LLMs via Step Entropy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal

August 11, 2025

Chengcheng Wan이 [arXiv]에 게시한 ‘Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reproducibility

[논문리뷰] A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code

September 1, 2025

Libo Chen이 [arXiv]에 게시한 ‘A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

August 12, 2025

Kai Zou이 [arXiv]에 게시한 ‘BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

데이터 필터링

[논문리뷰] POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion

September 3, 2025

Haicheng Wang이 [arXiv]에 게시한 ‘POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs

August 12, 2025

Robert Kirk이 [arXiv]에 게시한 ‘Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Misinformation

[논문리뷰] FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

August 21, 2025

tianlecai이 [arXiv]에 게시한 ‘FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System

August 12, 2025

Reynold Cheng이 [arXiv]에 게시한 ‘Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Rectified Flow

[논문리뷰] ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment

September 23, 2025

Yue Ma이 [arXiv]에 게시한 ‘ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control

August 12, 2025

Hongyu Liu이 [arXiv]에 게시한 ‘Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Compression

[논문리뷰] Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs

September 17, 2025

Luca Benini이 [arXiv]에 게시한 ‘Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs

August 12, 2025

Jianguo Li이 [arXiv]에 게시한 ‘MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Loss Aggregation

[논문리뷰] ΔL Normalization: Rethink Loss Aggregation in RLVR

September 10, 2025

Lili Qiu이 [arXiv]에 게시한 ‘ΔL Normalization: Rethink Loss Aggregation in RLVR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning

August 12, 2025

Jiaheng Liu이 [arXiv]에 게시한 ‘Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Generation

[논문리뷰] RewardDance: Reward Scaling in Visual Generation

September 11, 2025

Liang Li이 [arXiv]에 게시한 ‘RewardDance: Reward Scaling in Visual Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Reinforcement Learning in Vision: A Survey

August 12, 2025

Qingwei Meng이 [arXiv]에 게시한 ‘Reinforcement Learning in Vision: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Robot Learning

[논문리뷰] Robix: A Unified Model for Robot Interaction, Reasoning and Planning

September 4, 2025

Zixuan Wang이 [arXiv]에 게시한 ‘Robix: A Unified Model for Robot Interaction, Reasoning and Planning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation

August 12, 2025

Hengtao Shen이 [arXiv]에 게시한 ‘Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Retrieval

[논문리뷰] MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction

September 23, 2025

Xintao Chen이 [arXiv]에 게시한 ‘MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

August 12, 2025

Tong Yu이 [arXiv]에 게시한 ‘VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multilingual NLP

[논문리뷰] Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth

September 5, 2025

Chi-Li Chen이 [arXiv]에 게시한 ‘Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

August 12, 2025

Tong Yu이 [arXiv]에 게시한 ‘VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agentic Search

[논문리뷰] Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL

August 13, 2025

Chuyi He이 [arXiv]에 게시한 ‘Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WideSearch: Benchmarking Agentic Broad Info-Seeking

August 12, 2025

Yan Gao이 [arXiv]에 게시한 ‘WideSearch: Benchmarking Agentic Broad Info-Seeking’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Information Seeking

[논문리뷰] Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information

August 19, 2025

Xi Yang이 [arXiv]에 게시한 ‘Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WideSearch: Benchmarking Agentic Broad Info-Seeking

August 12, 2025

Yan Gao이 [arXiv]에 게시한 ‘WideSearch: Benchmarking Agentic Broad Info-Seeking’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

대규모 언어 모델

[논문리뷰] PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing

August 18, 2025

Xianpei Han이 [arXiv]에 게시한 ‘PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators

August 13, 2025

Tao Zhang이 [arXiv]에 게시한 ‘AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

멀티모달 AI

[논문리뷰] POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion

September 3, 2025

Haicheng Wang이 [arXiv]에 게시한 ‘POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators

August 13, 2025

Tao Zhang이 [arXiv]에 게시한 ‘AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Encoder-Decoder

[논문리뷰] Beyond Transcription: Mechanistic Interpretability in ASR

August 28, 2025

Aviv Shamsian이 [arXiv]에 게시한 ‘Beyond Transcription: Mechanistic Interpretability in ASR’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition

August 13, 2025

Lukáš Burget이 [arXiv]에 게시한 ‘DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Game AI

[논문리뷰] Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models

September 1, 2025

Yifan Lu이 [arXiv]에 게시한 ‘Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy

August 13, 2025

Elizabeth Karpinski이 [arXiv]에 게시한 ‘Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Deep Search

[논문리뷰] MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents

August 20, 2025

Jun Dong이 [arXiv]에 게시한 ‘MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches

August 13, 2025

Qiang Ju이 [arXiv]에 게시한 ‘HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D World Generation

[논문리뷰] LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation

September 8, 2025

Zhan Zhao이 [arXiv]에 게시한 ‘LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Matrix-3D: Omnidirectional Explorable 3D World Generation

August 13, 2025

Yuqi Li이 [arXiv]에 게시한 ‘Matrix-3D: Omnidirectional Explorable 3D World Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Large-scale Dataset

[논문리뷰] Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation

September 1, 2025

Qi Jia이 [arXiv]에 게시한 ‘Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OpenCUA: Open Foundations for Computer-Use Agents

August 13, 2025

Tianbao Xie이 [arXiv]에 게시한 ‘OpenCUA: Open Foundations for Computer-Use Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Test-Time Optimization

[논문리뷰] Deep Think with Confidence

August 22, 2025

Xuewei Wang이 [arXiv]에 게시한 ‘Deep Think with Confidence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models

August 14, 2025

Zeynep Akata이 [arXiv]에 게시한 ‘Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Question Answering

[논문리뷰] When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding

August 22, 2025

Rui Guo이 [arXiv]에 게시한 ‘When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory

August 14, 2025

Yuan Lin이 [arXiv]에 게시한 ‘Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning Benchmark

[논문리뷰] T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation

August 26, 2025

Xihui Liu이 [arXiv]에 게시한 ‘T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts

August 15, 2025

Rui Lu이 [arXiv]에 게시한 ‘PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image Processing

[논문리뷰] Thyme: Think Beyond Images

August 18, 2025

Wei Chen이 [arXiv]에 게시한 ‘Thyme: Think Beyond Images’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Processing and acquisition traces in visual encoders: What does CLIP know about your camera?

August 15, 2025

Giorgos Tolias이 [arXiv]에 게시한 ‘Processing and acquisition traces in visual encoders: What does CLIP know about your camera?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Distribution Shift

[논문리뷰] When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs

August 19, 2025

Elena Tutubalina이 [arXiv]에 게시한 ‘When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Processing and acquisition traces in visual encoders: What does CLIP know about your camera?

August 15, 2025

Giorgos Tolias이 [arXiv]에 게시한 ‘Processing and acquisition traces in visual encoders: What does CLIP know about your camera?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

DiT

[논문리뷰] Wan-Animate: Unified Character Animation and Replacement with Holistic Replication

September 18, 2025

Mingyang Huang이 [arXiv]에 게시한 ‘Wan-Animate: Unified Character Animation and Replacement with Holistic Replication’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing

August 15, 2025

Xiaoyu Li이 [arXiv]에 게시한 ‘ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Low-Rank Adaptation

[논문리뷰] LuxDiT: Lighting Estimation with Video Diffusion Transformer

September 8, 2025

Sanja Fidler이 [arXiv]에 게시한 ‘LuxDiT: Lighting Estimation with Video Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing

August 15, 2025

Xiaoyu Li이 [arXiv]에 게시한 ‘ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Animation

[논문리뷰] Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence

August 20, 2025

Xin Chen이 [arXiv]에 게시한 ‘Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing

August 15, 2025

Xiaoyu Li이 [arXiv]에 게시한 ‘ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Explainable AI (XAI)

[논문리뷰] Cross-Attention is Half Explanation in Speech-to-Text Models

September 23, 2025

Luisa Bentivogli이 [arXiv]에 게시한 ‘Cross-Attention is Half Explanation in Speech-to-Text Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing

August 15, 2025

Gjergji Kasneci이 [arXiv]에 게시한 ‘When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in...

Back to Top ↑

Human Feedback

[논문리뷰] IntrEx: A Dataset for Modeling Engagement in Educational Conversations

September 15, 2025

Gabriele Pergola이 [arXiv]에 게시한 ‘IntrEx: A Dataset for Modeling Engagement in Educational Conversations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

August 18, 2025

Mu Xu이 [arXiv]에 게시한 ‘FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal

[논문리뷰] M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision

September 3, 2025

Yan-Jie Zhou이 [arXiv]에 게시한 ‘M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data

August 18, 2025

Nicolas Gonthier이 [arXiv]에 게시한 ‘MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pseudo-labeling

[논문리뷰] When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs

September 23, 2025

Anand Mishra이 [arXiv]에 게시한 ‘When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs’ 논문에...

[논문리뷰] SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation

August 18, 2025

Paolo Soda이 [arXiv]에 게시한 ‘SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Knowledge Retrieval

[논문리뷰] Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning

August 27, 2025

Arman Cohan이 [arXiv]에 게시한 ‘Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] SSRL: Self-Search Reinforcement Learning

August 18, 2025

Yanxu Chen이 [arXiv]에 게시한 ‘SSRL: Self-Search Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Graph Neural Networks

[논문리뷰] Understanding Embedding Scaling in Collaborative Filtering

September 23, 2025

Yonghui Yang이 [arXiv]에 게시한 ‘Understanding Embedding Scaling in Collaborative Filtering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] X-Node: Self-Explanation is All We Need

August 18, 2025

Islem Rekik이 [arXiv]에 게시한 ‘X-Node: Self-Explanation is All We Need’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Point Clouds

[논문리뷰] MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

August 21, 2025

Jiangmiao이 [arXiv]에 게시한 ‘MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 4DNeX: Feed-Forward 4D Generative Modeling Made Easy

August 19, 2025

Zeng Tao이 [arXiv]에 게시한 ‘4DNeX: Feed-Forward 4D Generative Modeling Made Easy’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Transformer Networks

[논문리뷰] Representing Speech Through Autoregressive Prediction of Cochlear Tokens

August 19, 2025

Daniel L. K. Yamins이 [arXiv]에 게시한 ‘Representing Speech Through Autoregressive Prediction of Cochlear Tokens’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration

August 19, 2025

Evgeny Burnaev이 [arXiv]에 게시한 ‘G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AGI

[논문리뷰] GenExam: A Multidisciplinary Text-to-Image Exam

September 18, 2025

Yu Qiao이 [arXiv]에 게시한 ‘GenExam: A Multidisciplinary Text-to-Image Exam’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Has GPT-5 Achieved Spatial Intelligence? An Empirical Study

August 19, 2025

Ruisi Wang이 [arXiv]에 게시한 ‘Has GPT-5 Achieved Spatial Intelligence? An Empirical Study’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Editing

[논문리뷰] GenCompositor: Generative Video Compositing with Diffusion Transformer

September 3, 2025

Lingen Li이 [arXiv]에 게시한 ‘GenCompositor: Generative Video Compositing with Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models

August 19, 2025

Zixiang Gao이 [arXiv]에 게시한 ‘Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Deep Reasoning

[논문리뷰] Reverse-Engineered Reasoning for Open-Ended Generation

September 9, 2025

Wangchunshu Zhou이 [arXiv]에 게시한 ‘Reverse-Engineered Reasoning for Open-Ended Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Ovis2.5 Technical Report

August 19, 2025

Yang Li이 [arXiv]에 게시한 ‘Ovis2.5 Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

OCR

[논문리뷰] POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion

September 3, 2025

Haicheng Wang이 [arXiv]에 게시한 ‘POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Ovis2.5 Technical Report

August 19, 2025

Yang Li이 [arXiv]에 게시한 ‘Ovis2.5 Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

State Space Models

[논문리뷰] Autoregressive Universal Video Segmentation Model

August 27, 2025

Albert Gu이 [arXiv]에 게시한 ‘Autoregressive Universal Video Segmentation Model’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Speed Always Wins: A Survey on Efficient Architectures for Large Language Models

August 19, 2025

Jusen Du이 [arXiv]에 게시한 ‘Speed Always Wins: A Survey on Efficient Architectures for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Prompt Sensitivity

[논문리뷰] Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs

September 19, 2025

Katharina von der Wense이 [arXiv]에 게시한 ‘Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs

August 19, 2025

Elena Tutubalina이 [arXiv]에 게시한 ‘When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Proactive AI

[논문리뷰] Morae: Proactively Pausing UI Agents for User Choices

September 1, 2025

Amy Pavel이 [arXiv]에 게시한 ‘Morae: Proactively Pausing UI Agents for User Choices’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models

August 20, 2025

Zishang Jiang이 [arXiv]에 게시한 ‘A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Generation Process

[논문리뷰] Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation

August 20, 2025

Xinyi Wang이 [arXiv]에 게시한 ‘Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models

August 20, 2025

Zishang Jiang이 [arXiv]에 게시한 ‘A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adaptive Learning

[논문리뷰] Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding

September 10, 2025

Yongcheng Zeng이 [arXiv]에 게시한 ‘Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models

August 20, 2025

Zishang Jiang이 [arXiv]에 게시한 ‘A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Uncertainty Quantification

[논문리뷰] Why Language Models Hallucinate

September 8, 2025

Edwin Zhang이 [arXiv]에 게시한 ‘Why Language Models Hallucinate’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Beyond Human Judgment: A Bayesian Evaluation of LLMs’ Moral Values Understanding

August 20, 2025

Alina Landowska이 [arXiv]에 게시한 ‘Beyond Human Judgment: A Bayesian Evaluation of LLMs’ Moral Values Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Holistic Evaluation

[논문리뷰] AHELM: A Holistic Evaluation of Audio-Language Models

September 1, 2025

Siwei Yang이 [arXiv]에 게시한 ‘AHELM: A Holistic Evaluation of Audio-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence

August 20, 2025

Fernando López이 [arXiv]에 게시한 ‘MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Medical Image Segmentation

[논문리뷰] MedDINOv3: How to adapt vision foundation models for medical image segmentation?

September 3, 2025

Xiaofeng Yang이 [arXiv]에 게시한 ‘MedDINOv3: How to adapt vision foundation models for medical image segmentation?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation

August 20, 2025

Jonas Geiping이 [arXiv]에 게시한 ‘MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mask-Free

[논문리뷰] OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

September 23, 2025

Pengze Zhang이 [arXiv]에 게시한 ‘OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniTry: Virtual Try-On Anything without Masks

August 20, 2025

Xiaoduan Feng이 [arXiv]에 게시한 ‘OmniTry: Virtual Try-On Anything without Masks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image Inpainting

[논문리뷰] 2D Gaussian Splatting with Semantic Alignment for Image Inpainting

September 12, 2025

Guangming Lu이 [arXiv]에 게시한 ‘2D Gaussian Splatting with Semantic Alignment for Image Inpainting’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniTry: Virtual Try-On Anything without Masks

August 20, 2025

Xiaoduan Feng이 [arXiv]에 게시한 ‘OmniTry: Virtual Try-On Anything without Masks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Systematic Review

[논문리뷰] A Survey on Large Language Model Benchmarks

August 22, 2025

Siyi Li이 [arXiv]에 게시한 ‘A Survey on Large Language Model Benchmarks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research

August 20, 2025

Susanne Schmidt이 [arXiv]에 게시한 ‘Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Attention Control

[논문리뷰] LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence

September 16, 2025

Lionel M. Ni이 [arXiv]에 게시한 ‘LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer

August 20, 2025

Deyu Zhou이 [arXiv]에 게시한 ‘Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Optimization

[논문리뷰] Single-stream Policy Optimization

September 17, 2025

Zihan Ding이 [arXiv]에 게시한 ‘Single-stream Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

August 21, 2025

Yu Lu이 [arXiv]에 게시한 ‘DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AI for Science

[논문리뷰] A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers

September 1, 2025

Jiamin Wu이 [arXiv]에 게시한 ‘A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery

August 21, 2025

zijieqiu이 [arXiv]에 게시한 ‘From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Financial LLMs

[논문리뷰] FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning

September 19, 2025

Jiashuo Liu이 [arXiv]에 게시한 ‘FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models

August 21, 2025

Ziyan Kuang이 [arXiv]에 게시한 ‘From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Live Benchmark

[논문리뷰] DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis

August 28, 2025

Ion Stoica이 [arXiv]에 게시한 ‘DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

August 21, 2025

tianlecai이 [arXiv]에 게시한 ‘FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Contamination

[논문리뷰] A Survey on Large Language Model Benchmarks

August 22, 2025

Siyi Li이 [arXiv]에 게시한 ‘A Survey on Large Language Model Benchmarks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

August 21, 2025

tianlecai이 [arXiv]에 게시한 ‘FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Web Search

[논문리뷰] ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization

September 17, 2025

Litu Ou이 [arXiv]에 게시한 ‘ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

August 21, 2025

tianlecai이 [arXiv]에 게시한 ‘FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

FP8 Training

[논문리뷰] Metis: Training Large Language Models with Advanced Low-Bit Quantization

September 3, 2025

Hengjie Cao이 [arXiv]에 게시한 ‘Metis: Training Large Language Models with Advanced Low-Bit Quantization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

August 21, 2025

abercovich이 [arXiv]에 게시한 ‘NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Editing

[논문리뷰] VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space

August 27, 2025

Rui Chen이 [arXiv]에 게시한 ‘VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Tinker: Diffusion’s Gift to 3D–Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization

August 21, 2025

Hao Chen이 [arXiv]에 게시한 ‘Tinker: Diffusion’s Gift to 3D–Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-View Consistency

[논문리뷰] VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

September 24, 2025

Haoxiao Wang이 [arXiv]에 게시한 ‘VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Tinker: Diffusion’s Gift to 3D–Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization

August 21, 2025

Hao Chen이 [arXiv]에 게시한 ‘Tinker: Diffusion’s Gift to 3D–Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Educational Assessment

[논문리뷰] MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment

August 26, 2025

Doratossadat Dastgheib이 [arXiv]에 게시한 ‘MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?

August 21, 2025

Daeyoung Kim이 [arXiv]에 게시한 ‘ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Commonsense Reasoning

[논문리뷰] The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang

September 3, 2025

Solomon Tsai이 [arXiv]에 게시한 ‘The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning

August 21, 2025

anoperson이 [arXiv]에 게시한 ‘mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AI Ethics

[논문리뷰] EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI

September 16, 2025

UVSKKR이 [arXiv]에 게시한 ‘EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] A Survey on Large Language Model Benchmarks

August 22, 2025

Siyi Li이 [arXiv]에 게시한 ‘A Survey on Large Language Model Benchmarks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Language Models (LLMs)

[논문리뷰] Universal Deep Research: Bring Your Own Model and Strategy

September 3, 2025

Pavlo Molchanov이 [arXiv]에 게시한 ‘Universal Deep Research: Bring Your Own Model and Strategy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] INTIMA: A Benchmark for Human-AI Companionship Behavior

August 22, 2025

Yacine Jernite이 [arXiv]에 게시한 ‘INTIMA: A Benchmark for Human-AI Companionship Behavior’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Agents

[논문리뷰] Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models

September 16, 2025

Shuo Ren이 [arXiv]에 게시한 ‘Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Mobile-Agent-v3: Foundamental Agents for GUI Automation

August 22, 2025

Haowei Liu이 [arXiv]에 게시한 ‘Mobile-Agent-v3: Foundamental Agents for GUI Automation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Temporal Grounding

[논문리뷰] TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

September 23, 2025

Shaohui Jiao이 [arXiv]에 게시한 ‘TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding

August 22, 2025

Rui Guo이 [arXiv]에 게시한 ‘When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scientific Discovery

[논문리뷰] Spacer: Towards Engineered Scientific Inspiration

August 27, 2025

zerojun48이 [arXiv]에 게시한 ‘Spacer: Towards Engineered Scientific Inspiration’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists

August 22, 2025

Heng Zhang이 [arXiv]에 게시한 ‘aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Parameter-Efficient Fine-Tuning

[논문리뷰] LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios

September 15, 2025

Bing Su이 [arXiv]에 게시한 ‘LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CRISP: Persistent Concept Unlearning via Sparse Autoencoders

August 25, 2025

Yonatan Belinkov이 [arXiv]에 게시한 ‘CRISP: Persistent Concept Unlearning via Sparse Autoencoders’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human-Robot Interaction

[논문리뷰] Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue

September 22, 2025

Hui Zhang이 [arXiv]에 게시한 ‘Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Do What? Teaching Vision-Language-Action Models to Reject the Impossible

August 25, 2025

Roei Herzig이 [arXiv]에 게시한 ‘Do What? Teaching Vision-Language-Action Models to Reject the Impossible’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Medical Diagnosis

[논문리뷰] EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence

September 19, 2025

Qinghua Huang이 [arXiv]에 게시한 ‘EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning

August 25, 2025

Pengcheng Qiu이 [arXiv]에 게시한 ‘End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Clinical Decision Support

[논문리뷰] EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI

September 16, 2025

UVSKKR이 [arXiv]에 게시한 ‘EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning

August 25, 2025

Pengcheng Qiu이 [arXiv]에 게시한 ‘End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Out-of-Distribution Generalization

[논문리뷰] False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize

September 5, 2025

Muhao Chen이 [arXiv]에 게시한 ‘False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning

August 25, 2025

Pengcheng Qiu이 [arXiv]에 게시한 ‘End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adaptive Reasoning

[논문리뷰] Visual Programmability: A Guide for Code-as-Thought in Chart Understanding

September 12, 2025

Ethan Chern이 [arXiv]에 게시한 ‘Visual Programmability: A Guide for Code-as-Thought in Chart Understanding’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles

August 25, 2025

Diping Song이 [arXiv]에 게시한 ‘InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Neural Networks

[논문리뷰] ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association

September 3, 2025

Daniel Cremers이 [arXiv]에 게시한 ‘ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics

August 25, 2025

Xiao Sun이 [arXiv]에 게시한 ‘Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Paraphrasing

[논문리뷰] On Robustness and Reliability of Benchmark-Based Evaluation of LLMs

September 8, 2025

Kevin Roitero이 [arXiv]에 게시한 ‘On Robustness and Reliability of Benchmark-Based Evaluation of LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German

August 26, 2025

Cristian-George Craciun이 [arXiv]에 게시한 ‘German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Accessibility

[논문리뷰] Morae: Proactively Pausing UI Agents for User Choices

September 1, 2025

Amy Pavel이 [arXiv]에 게시한 ‘Morae: Proactively Pausing UI Agents for User Choices’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German

August 26, 2025

Cristian-George Craciun이 [arXiv]에 게시한 ‘German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Inference Efficiency

[논문리뷰] TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling

August 27, 2025

Zhoufutu Wen이 [arXiv]에 게시한 ‘TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling’ 논문에 대한 ...

[논문리뷰] InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

August 26, 2025

jinglinglin이 [arXiv]에 게시한 ‘InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Context Length

[논문리뷰] LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering

September 12, 2025

Jianguo Zhang이 [arXiv]에 게시한 ‘LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Limitations of Normalization in Attention Mechanism

August 26, 2025

Radu State이 [arXiv]에 게시한 ‘Limitations of Normalization in Attention Mechanism’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Consistency

[논문리뷰] VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space

August 27, 2025

Rui Chen이 [arXiv]에 게시한 ‘VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MV-RAG: Retrieval Augmented Multiview Diffusion

August 26, 2025

sagiebenaim이 [arXiv]에 게시한 ‘MV-RAG: Retrieval Augmented Multiview Diffusion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Surface Reconstruction

[논문리뷰] GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction

September 24, 2025

Jin Zheng이 [arXiv]에 게시한 ‘GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting

August 26, 2025

Yanzhe Liang이 [arXiv]에 게시한 ‘MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Speech Tokenizer

[논문리뷰] VibeVoice Technical Report

August 27, 2025

Yaoyao Chang이 [arXiv]에 게시한 ‘VibeVoice Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling

August 26, 2025

Jiaqi Li이 [arXiv]에 게시한 ‘TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semantic Reasoning

[논문리뷰] Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth

September 5, 2025

Chi-Li Chen이 [arXiv]에 게시한 ‘Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation

August 26, 2025

Haoxiang Shi이 [arXiv]에 게시한 ‘Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Autoregressive Model

[논문리뷰] MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

September 22, 2025

jialingt이 [arXiv]에 게시한 ‘MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Autoregressive Universal Video Segmentation Model

August 27, 2025

Albert Gu이 [arXiv]에 게시한 ‘Autoregressive Universal Video Segmentation Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Parallel Training

[논문리뷰] Causal Attention with Lookahead Keys

September 10, 2025

Quanquan Gu이 [arXiv]에 게시한 ‘Causal Attention with Lookahead Keys’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Autoregressive Universal Video Segmentation Model

August 27, 2025

Albert Gu이 [arXiv]에 게시한 ‘Autoregressive Universal Video Segmentation Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Benchmarks

[논문리뷰] MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools

September 15, 2025

Xiaorui Wang이 [arXiv]에 게시한 ‘MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning

August 27, 2025

Arman Cohan이 [arXiv]에 게시한 ‘Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Diffusion Transformers (DiT)

[논문리뷰] Mixture of Contexts for Long Video Generation

August 29, 2025

Junfei Xiao이 [arXiv]에 게시한 ‘Mixture of Contexts for Long Video Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation

August 27, 2025

Jiaqi Yang이 [arXiv]에 게시한 ‘OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Generalization Gap

[논문리뷰] TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis

September 1, 2025

Pengcheng Chen이 [arXiv]에 게시한 ‘TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks

August 27, 2025

Daisuke Nohara이 [arXiv]에 게시한 ‘Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Neural Radiance Fields

[논문리뷰] GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction

September 24, 2025

Jin Zheng이 [arXiv]에 게시한 ‘GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels

August 27, 2025

Dinesh Jayaraman이 [arXiv]에 게시한 ‘Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semantic Features

[논문리뷰] X-Part: high fidelity and structure coherent shape decomposition

September 15, 2025

Yunhan Yang이 [arXiv]에 게시한 ‘X-Part: high fidelity and structure coherent shape decomposition’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting

August 27, 2025

Manuela Veloso이 [arXiv]에 게시한 ‘QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Deep Research Agents

[논문리뷰] Scaling Agents via Continual Pre-training

September 17, 2025

Guangyu Li이 [arXiv]에 게시한 ‘Scaling Agents via Continual Pre-training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks

August 27, 2025

Kai Jia이 [arXiv]에 게시한 ‘ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Factual Accuracy

[논문리뷰] Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet

September 9, 2025

See-Kiong Ng이 [arXiv]에 게시한 ‘Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks

August 27, 2025

Kai Jia이 [arXiv]에 게시한 ‘ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Report Generation

[논문리뷰] EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence

September 19, 2025

Qinghua Huang이 [arXiv]에 게시한 ‘EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks

August 27, 2025

Kai Jia이 [arXiv]에 게시한 ‘ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Research Automation

[논문리뷰] Universal Deep Research: Bring Your Own Model and Strategy

September 3, 2025

Pavlo Molchanov이 [arXiv]에 게시한 ‘Universal Deep Research: Bring Your Own Model and Strategy’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Spacer: Towards Engineered Scientific Inspiration

August 27, 2025

zerojun48이 [arXiv]에 게시한 ‘Spacer: Towards Engineered Scientific Inspiration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vulnerability Detection

[논문리뷰] A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code

September 1, 2025

Libo Chen이 [arXiv]에 게시한 ‘A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Training Language Model Agents to Find Vulnerabilities with CTF-Dojo

August 27, 2025

Zijian Wang이 [arXiv]에 게시한 ‘Training Language Model Agents to Find Vulnerabilities with CTF-Dojo’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Tree Search

[논문리뷰] Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers

September 9, 2025

Xia Xiao이 [arXiv]에 게시한 ‘Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling

August 27, 2025

Zhoufutu Wen이 [arXiv]에 게시한 ‘TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling’ 논문에 대한 ...

Back to Top ↑

Advantage Estimation

[논문리뷰] PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning

September 2, 2025

Yuewei Zhang이 [arXiv]에 게시한 ‘PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling

August 27, 2025

Zhoufutu Wen이 [arXiv]에 게시한 ‘TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling’ 논문에 대한 ...

Back to Top ↑

Mixture of Experts (MoE)

[논문리뷰] Benchmarking Optimizers for Large Language Model Pretraining

September 3, 2025

mjaggi이 [arXiv]에 게시한 ‘Benchmarking Optimizers for Large Language Model Pretraining’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning

August 27, 2025

Ran Guo이 [arXiv]에 게시한 ‘UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Robot Control

[논문리뷰] EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control

September 1, 2025

Zhaoqing Chen이 [arXiv]에 게시한 ‘EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies

August 28, 2025

Sitong Mao이 [arXiv]에 게시한 ‘Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Streaming Inference

[논문리뷰] EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs

September 12, 2025

Kaiqi Kou이 [arXiv]에 게시한 ‘EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation

August 28, 2025

Yan Zhou이 [arXiv]에 게시한 ‘MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Preference Alignment

[논문리뷰] Improving Large Vision and Language Models by Learning from a Panel of Peers

September 3, 2025

Simon Jenni이 [arXiv]에 게시한 ‘Improving Large Vision and Language Models by Learning from a Panel of Peers’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment

August 28, 2025

An-An Liu이 [arXiv]에 게시한 ‘MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Next-Token Prediction

[논문리뷰] Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation

September 19, 2025

Xihui Liu이 [arXiv]에 게시한 ‘Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Predicting the Order of Upcoming Tokens Improves Language Modeling

August 28, 2025

Alham Fikri Aji이 [arXiv]에 게시한 ‘Predicting the Order of Upcoming Tokens Improves Language Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Fine-tuning

[논문리뷰] QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models

September 23, 2025

Jae-Joon Kim이 [arXiv]에 게시한 ‘QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AWorld: Orchestrating the Training Recipe for Agentic AI

August 29, 2025

Qintong Wu이 [arXiv]에 게시한 ‘AWorld: Orchestrating the Training Recipe for Agentic AI’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sparsification

[논문리뷰] Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs

September 17, 2025

Luca Benini이 [arXiv]에 게시한 ‘Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification

August 29, 2025

Liqiang Nie이 [arXiv]에 게시한 ‘CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image-to-3D

[논문리뷰] Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation

September 1, 2025

Qi Jia이 [arXiv]에 게시한 ‘Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Collaborative Multi-Modal Coding for High-Quality 3D Generation

August 29, 2025

Ziwei Liu이 [arXiv]에 게시한 ‘Collaborative Multi-Modal Coding for High-Quality 3D Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Diffusion

[논문리뷰] VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models

September 23, 2025

Sunghyun Cho이 [arXiv]에 게시한 ‘VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Dress&Dance: Dress up and Dance as You Like It - Technical Preview

August 29, 2025

Yu-Xiong Wang이 [arXiv]에 게시한 ‘Dress&Dance: Dress up and Dance as You Like It - Technical Preview’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human Perception

[논문리뷰] Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems

September 22, 2025

Hung-yi Lee이 [arXiv]에 게시한 ‘Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems’ 논문에 대...

[논문리뷰] FakeParts: a New Family of AI-Generated DeepFakes

August 29, 2025

Xi Wang이 [arXiv]에 게시한 ‘FakeParts: a New Family of AI-Generated DeepFakes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dynamic Scenes

[논문리뷰] RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes

September 22, 2025

Narendra Ahuja이 [arXiv]에 게시한 ‘RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Multi-View 3D Point Tracking

August 29, 2025

Irem Demir이 [arXiv]에 게시한 ‘Multi-View 3D Point Tracking’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image Customization

[논문리뷰] UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward

September 10, 2025

Fei Ding이 [arXiv]에 게시한 ‘UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning

August 29, 2025

Jiahe Tian이 [arXiv]에 게시한 ‘USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Evaluation Benchmark

[논문리뷰] LIMI: Less is More for Agency

September 23, 2025

happyZYM이 [arXiv]에 게시한 ‘LIMI: Less is More for Agency’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis

September 1, 2025

Pengcheng Chen이 [arXiv]에 게시한 ‘TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Function Calling

[논문리뷰] Towards General Agentic Intelligence via Environment Scaling

September 17, 2025

Guangyu Li이 [arXiv]에 게시한 ‘Towards General Agentic Intelligence via Environment Scaling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench

September 2, 2025

Jayanth Srinivasa이 [arXiv]에 게시한 ‘How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench’ 논문에 대한 자세한 리뷰입...

Back to Top ↑

Dynamic Environments

[논문리뷰] The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

September 3, 2025

Hejia Geng이 [arXiv]에 게시한 ‘The Landscape of Agentic Reinforcement Learning for LLMs: A Survey’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench

September 2, 2025

Jayanth Srinivasa이 [arXiv]에 게시한 ‘How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench’ 논문에 대한 자세한 리뷰입...

Back to Top ↑

Speculative Decoding

[논문리뷰] Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation

September 24, 2025

Jianbin Zheng이 [arXiv]에 게시한 ‘Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models

September 3, 2025

Rahul Karthikeyan이 [arXiv]에 게시한 ‘AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Al...

Back to Top ↑

Hyperparameter Tuning

[논문리뷰] Fantastic Pretraining Optimizers and Where to Find Them

September 3, 2025

Percy Liang이 [arXiv]에 게시한 ‘Fantastic Pretraining Optimizers and Where to Find Them’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Benchmarking Optimizers for Large Language Model Pretraining

September 3, 2025

mjaggi이 [arXiv]에 게시한 ‘Benchmarking Optimizers for Large Language Model Pretraining’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AdamW

[논문리뷰] Fantastic Pretraining Optimizers and Where to Find Them

September 3, 2025

Percy Liang이 [arXiv]에 게시한 ‘Fantastic Pretraining Optimizers and Where to Find Them’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Benchmarking Optimizers for Large Language Model Pretraining

September 3, 2025

mjaggi이 [arXiv]에 게시한 ‘Benchmarking Optimizers for Large Language Model Pretraining’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Positional Encoding

[논문리뷰] Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views

September 3, 2025

Junchi Yan이 [arXiv]에 게시한 ‘Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Vie...

[논문리뷰] ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding

September 3, 2025

Xuanyu Zheng이 [arXiv]에 게시한 ‘ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Improvement

[논문리뷰] Bootstrapping Task Spaces for Self-Improvement

September 8, 2025

Yoram Bachrach이 [arXiv]에 게시한 ‘Bootstrapping Task Spaces for Self-Improvement’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Improving Large Vision and Language Models by Learning from a Panel of Peers

September 3, 2025

Simon Jenni이 [arXiv]에 게시한 ‘Improving Large Vision and Language Models by Learning from a Panel of Peers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Knowledge Transfer

[논문리뷰] When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs

September 23, 2025

Anand Mishra이 [arXiv]에 게시한 ‘When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs’ 논문에...

[논문리뷰] Improving Large Vision and Language Models by Learning from a Panel of Peers

September 3, 2025

Simon Jenni이 [arXiv]에 게시한 ‘Improving Large Vision and Language Models by Learning from a Panel of Peers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

DINOv3

[논문리뷰] Does DINOv3 Set a New Medical Vision Standard?

September 9, 2025

Bailiang Jian이 [arXiv]에 게시한 ‘Does DINOv3 Set a New Medical Vision Standard?’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MedDINOv3: How to adapt vision foundation models for medical image segmentation?

September 3, 2025

Xiaofeng Yang이 [arXiv]에 게시한 ‘MedDINOv3: How to adapt vision foundation models for medical image segmentation?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Collection

[논문리뷰] U-ARM : Ultra low-cost general teleoperation interface for robot manipulation

September 8, 2025

Junda Huang이 [arXiv]에 게시한 ‘U-ARM : Ultra low-cost general teleoperation interface for robot manipulation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MobiAgent: A Systematic Framework for Customizable Mobile Agents

September 3, 2025

Wangbo Gong이 [arXiv]에 게시한 ‘MobiAgent: A Systematic Framework for Customizable Mobile Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agent Framework

[논문리뷰] AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning

September 11, 2025

Honglin Guo이 [arXiv]에 게시한 ‘AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

September 3, 2025

Haoyang Zou이 [arXiv]에 게시한 ‘UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agentic Systems

[논문리뷰] Single-stream Policy Optimization

September 17, 2025

Zihan Ding이 [arXiv]에 게시한 ‘Single-stream Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Universal Deep Research: Bring Your Own Model and Strategy

September 3, 2025

Pavlo Molchanov이 [arXiv]에 게시한 ‘Universal Deep Research: Bring Your Own Model and Strategy’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Few-Step Generation

[논문리뷰] Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling

September 10, 2025

Diana Marculescu이 [arXiv]에 게시한 ‘Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Transition Models: Rethinking the Generative Learning Objective

September 5, 2025

Yangguang Li이 [arXiv]에 게시한 ‘Transition Models: Rethinking the Generative Learning Objective’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Turn Reasoning

[논문리뷰] Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search

September 10, 2025

Tianjian Li이 [arXiv]에 게시한 ‘Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding

September 5, 2025

Lionel Ni이 [arXiv]에 게시한 ‘Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Procedural Content Generation

[논문리뷰] Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning

September 23, 2025

Damien Sileo이 [arXiv]에 게시한 ‘Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation

September 8, 2025

Zhan Zhao이 [arXiv]에 게시한 ‘LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dataset Annotation

[논문리뷰] IntrEx: A Dataset for Modeling Engagement in Educational Conversations

September 15, 2025

Gabriele Pergola이 [arXiv]에 게시한 ‘IntrEx: A Dataset for Modeling Engagement in Educational Conversations’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning

September 9, 2025

Dhanvin Sanjay Namboodiri이 [arXiv]에 게시한 ‘D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM-based Agents

[논문리뷰] EnvX: Agentize Everything with Agentic AI

September 11, 2025

Wenzheng Tom Tang이 [arXiv]에 게시한 ‘EnvX: Agentize Everything with Agentic AI’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents

September 9, 2025

Zhengxi Lu이 [arXiv]에 게시한 ‘MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Natural Language Interaction

[논문리뷰] EnvX: Agentize Everything with Agentic AI

September 11, 2025

Wenzheng Tom Tang이 [arXiv]에 게시한 ‘EnvX: Agentize Everything with Agentic AI’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents

September 9, 2025

James Zou이 [arXiv]에 게시한 ‘Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adversarial Training

[논문리뷰] Language Self-Play For Data-Free Training

September 10, 2025

Vijai Mohan이 [arXiv]에 게시한 ‘Language Self-Play For Data-Free Training’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World

September 9, 2025

Bowen Zhou이 [arXiv]에 게시한 ‘R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Web Agents

[논문리뷰] WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning

September 17, 2025

Huifeng Yin이 [arXiv]에 게시한 ‘WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents

September 9, 2025

Aili Chen이 [arXiv]에 게시한 ‘WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long-Horizon Reasoning

[논문리뷰] ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization

September 17, 2025

Litu Ou이 [arXiv]에 게시한 ‘ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents

September 9, 2025

Aili Chen이 [arXiv]에 게시한 ‘WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Generation

[논문리뷰] Mano Report

September 23, 2025

Minghui Wu이 [arXiv]에 게시한 ‘Mano Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents

September 9, 2025

Aili Chen이 [arXiv]에 게시한 ‘WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

4D World Modeling

[논문리뷰] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

September 16, 2025

Yang Zhou이 [arXiv]에 게시한 ‘OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] 3D and 4D World Modeling: A Survey

September 11, 2025

Ao Liang이 [arXiv]에 게시한 ‘3D and 4D World Modeling: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Machine Translation

[논문리뷰] Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale

September 18, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Hunyuan-MT Technical Report

September 11, 2025

Yang Du이 [arXiv]에 게시한 ‘Hunyuan-MT Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multilingual

[논문리뷰] VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions

September 15, 2025

Dong Zhang이 [arXiv]에 게시한 ‘VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Hunyuan-MT Technical Report

September 11, 2025

Yang Du이 [arXiv]에 게시한 ‘Hunyuan-MT Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Slow Thinking

[논문리뷰] Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models

September 16, 2025

Shuo Ren이 [arXiv]에 게시한 ‘Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Hunyuan-MT Technical Report

September 11, 2025

Yang Du이 [arXiv]에 게시한 ‘Hunyuan-MT Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Style Transfer

[논문리뷰] MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks

September 19, 2025

Xijun Gu이 [arXiv]에 게시한 ‘MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] So let's replace this phrase with insult... Lessons learned from generation of toxic texts with LLMs

September 11, 2025

Alexander Panchenko이 [arXiv]에 게시한 ‘ So let's replace this phrase with insult... Lessons learned from generation of toxic texts with LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Unified Models

[논문리뷰] Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation

September 24, 2025

Jianbin Zheng이 [arXiv]에 게시한 ‘Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] Can Understanding and Generation Truly Benefit Together – or Just Coexist?

September 12, 2025

Hui Han이 [arXiv]에 게시한 ‘Can Understanding and Generation Truly Benefit Together – or Just Coexist?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Efficient AI

[논문리뷰] FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies

September 15, 2025

Fabian Otto이 [arXiv]에 게시한 ‘FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

September 12, 2025

Zirui Ge이 [arXiv]에 게시한 ‘VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-hop QA

[논문리뷰] FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning

September 19, 2025

Jiashuo Liu이 [arXiv]에 게시한 ‘FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering

September 15, 2025

Zhehao Tan이 [arXiv]에 게시한 ‘HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-turn Interaction

[논문리뷰] RecoWorld: Building Simulated Environments for Agentic Recommender Systems

September 19, 2025

Mingyuan Wu이 [arXiv]에 게시한 ‘RecoWorld: Building Simulated Environments for Agentic Recommender Systems’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning

September 16, 2025

Yongliang Shen이 [arXiv]에 게시한 ‘UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Context Management

[논문리뷰] WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents

September 17, 2025

Wenbiao Yin이 [arXiv]에 게시한 ‘WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization

September 17, 2025

Litu Ou이 [arXiv]에 게시한 ‘ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

State-of-the-Art

[논문리뷰] Qwen3-Omni Technical Report

September 23, 2025

Lhma-aslp이 [arXiv]에 게시한 ‘Qwen3-Omni Technical Report’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research

September 17, 2025

Houquan Zhou이 [arXiv]에 게시한 ‘WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mode Collapse

[논문리뷰] CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching

September 24, 2025

Rui Qian이 [arXiv]에 게시한 ‘CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] FlowRL: Matching Reward Distributions for LLM Reasoning

September 19, 2025

Hengli Li이 [arXiv]에 게시한 ‘FlowRL: Matching Reward Distributions for LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Memory Efficiency

[논문리뷰] HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis

September 24, 2025

Dan Xu이 [arXiv]에 게시한 ‘HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis’ 논문에 대한 자세한 리뷰입니다.

[논문리뷰] EpiCache: Episodic KV Cache Management for Long Conversational Question Answering

September 23, 2025

Minsik Cho이 [arXiv]에 게시한 ‘EpiCache: Episodic KV Cache Management for Long Conversational Question Answering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

SafeLine

[SafeLine] SafeLine 초기 설정

January 2, 2025

SafeLine 초기 설정 방법을 공유합니다.

Back to Top ↑

Logging

[Python] logging 사용법

January 3, 2025

Loguru 을 이용한 logging 간단하게 사용해보자

Back to Top ↑

GitHub Actions

[GitHub Actions] 깃허브 프로필 자동 업데이트하기

January 14, 2025

GitHub Actions를 이용해 깃허브 프로필을 자동으로 업데이트하는 방법을 공유합니다.

Back to Top ↑

Nginx

[Nginx] Let’s Encrypt로 SSL 인증서 발급받기

January 17, 2025

Let’s Encrypt로 SSL 인증서를 발급받는 방법을 공유합니다.

Back to Top ↑

Chrome Extension

[Chrome Extention] YouTube 차단 확장 프로그램 개발하기

February 25, 2025

YouTube 접속을 차단하고 생산성을 높이는 크롬 확장 프로그램을 만들어보세요. 개발 과정과 설치 방법을 자세히 설명합니다.

Back to Top ↑

AWS

[AWS] AWS Lambda와 Notion API를 활용한 15분 단위 자동 기록 시스템

February 25, 2025

AWS Lambda, Notion API, Slack Webhook을 활용하여 15분마다 자동으로 시간을 기록하고 Slack 알림을 받는 시스템을 구축하는 방법을 설명합니다.

Back to Top ↑

Lambda

[AWS] AWS Lambda와 Notion API를 활용한 15분 단위 자동 기록 시스템

February 25, 2025

AWS Lambda, Notion API, Slack Webhook을 활용하여 15분마다 자동으로 시간을 기록하고 Slack 알림을 받는 시스템을 구축하는 방법을 설명합니다.

Back to Top ↑

EventBridge

[AWS] AWS Lambda와 Notion API를 활용한 15분 단위 자동 기록 시스템

February 25, 2025

AWS Lambda, Notion API, Slack Webhook을 활용하여 15분마다 자동으로 시간을 기록하고 Slack 알림을 받는 시스템을 구축하는 방법을 설명합니다.

Back to Top ↑

Agriculture

[논문리뷰] AgroBench: Vision-Language Model Benchmark in Agriculture

August 3, 2025

Yoshitaka Ushiku이 [arXiv]에 게시한 ‘AgroBench: Vision-Language Model Benchmark in Agriculture’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Disease Identification

[논문리뷰] AgroBench: Vision-Language Model Benchmark in Agriculture

August 3, 2025

Yoshitaka Ushiku이 [arXiv]에 게시한 ‘AgroBench: Vision-Language Model Benchmark in Agriculture’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pest Management

[논문리뷰] AgroBench: Vision-Language Model Benchmark in Agriculture

August 3, 2025

Yoshitaka Ushiku이 [arXiv]에 게시한 ‘AgroBench: Vision-Language Model Benchmark in Agriculture’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Crop Management

[논문리뷰] AgroBench: Vision-Language Model Benchmark in Agriculture

August 3, 2025

Yoshitaka Ushiku이 [arXiv]에 게시한 ‘AgroBench: Vision-Language Model Benchmark in Agriculture’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agronomy

[논문리뷰] AgroBench: Vision-Language Model Benchmark in Agriculture

August 3, 2025

Yoshitaka Ushiku이 [arXiv]에 게시한 ‘AgroBench: Vision-Language Model Benchmark in Agriculture’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Kolmogorov-Arnold Networks

[논문리뷰] Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification

August 3, 2025

Abdelmalik Taleb-Ahmed이 [arXiv]에 게시한 ‘Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification’ 논문에 대한 ...

Back to Top ↑

Art Style Classification

[논문리뷰] Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification

August 3, 2025

Abdelmalik Taleb-Ahmed이 [arXiv]에 게시한 ‘Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification’ 논문에 대한 ...

Back to Top ↑

Spline-Based Activation

[논문리뷰] Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification

August 3, 2025

Abdelmalik Taleb-Ahmed이 [arXiv]에 게시한 ‘Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification’ 논문에 대한 ...

Back to Top ↑

Dual-Teacher

[논문리뷰] Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification

August 3, 2025

Abdelmalik Taleb-Ahmed이 [arXiv]에 게시한 ‘Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification’ 논문에 대한 ...

Back to Top ↑

Gram Matrix

[논문리뷰] Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification

August 3, 2025

Abdelmalik Taleb-Ahmed이 [arXiv]에 게시한 ‘Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification’ 논문에 대한 ...

Back to Top ↑

Spoken Dialogue Models

[논문리뷰] C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations

August 3, 2025

Yiwen Guo이 [arXiv]에 게시한 ‘C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bilingual Benchmark

[논문리뷰] C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations

August 3, 2025

Yiwen Guo이 [arXiv]에 게시한 ‘C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Complex Conversations

[논문리뷰] C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations

August 3, 2025

Yiwen Guo이 [arXiv]에 게시한 ‘C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Context Understanding

[논문리뷰] C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations

August 3, 2025

Yiwen Guo이 [arXiv]에 게시한 ‘C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Influence Function

[논문리뷰] Efficient Machine Unlearning via Influence Approximation

August 3, 2025

Enhong Chen이 [arXiv]에 게시한 ‘Efficient Machine Unlearning via Influence Approximation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Incremental Learning

[논문리뷰] Efficient Machine Unlearning via Influence Approximation

August 3, 2025

Enhong Chen이 [arXiv]에 게시한 ‘Efficient Machine Unlearning via Influence Approximation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Privacy Protection

[논문리뷰] Efficient Machine Unlearning via Influence Approximation

August 3, 2025

Enhong Chen이 [arXiv]에 게시한 ‘Efficient Machine Unlearning via Influence Approximation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gradient Optimization

[논문리뷰] Efficient Machine Unlearning via Influence Approximation

August 3, 2025

Enhong Chen이 [arXiv]에 게시한 ‘Efficient Machine Unlearning via Influence Approximation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dense Passage Retrieval

[논문리뷰] Enhanced Arabic Text Retrieval with Attentive Relevance Scoring

August 3, 2025

Abdenour Hadid이 [arXiv]에 게시한 ‘Enhanced Arabic Text Retrieval with Attentive Relevance Scoring’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Attentive Relevance Scoring

[논문리뷰] Enhanced Arabic Text Retrieval with Attentive Relevance Scoring

August 3, 2025

Abdenour Hadid이 [arXiv]에 게시한 ‘Enhanced Arabic Text Retrieval with Attentive Relevance Scoring’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semantic Matching

[논문리뷰] Enhanced Arabic Text Retrieval with Attentive Relevance Scoring

August 3, 2025

Abdenour Hadid이 [arXiv]에 게시한 ‘Enhanced Arabic Text Retrieval with Attentive Relevance Scoring’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Flow Equivariance

[논문리뷰] Flow Equivariant Recurrent Neural Networks

August 3, 2025

T. Anderson Keller이 [arXiv]에 게시한 ‘Flow Equivariant Recurrent Neural Networks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Recurrent Neural Networks

[논문리뷰] Flow Equivariant Recurrent Neural Networks

August 3, 2025

T. Anderson Keller이 [arXiv]에 게시한 ‘Flow Equivariant Recurrent Neural Networks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sequence Models

[논문리뷰] Flow Equivariant Recurrent Neural Networks

August 3, 2025

T. Anderson Keller이 [arXiv]에 게시한 ‘Flow Equivariant Recurrent Neural Networks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Group Equivariance

[논문리뷰] Flow Equivariant Recurrent Neural Networks

August 3, 2025

T. Anderson Keller이 [arXiv]에 게시한 ‘Flow Equivariant Recurrent Neural Networks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Lie Subgroups

[논문리뷰] Flow Equivariant Recurrent Neural Networks

August 3, 2025

T. Anderson Keller이 [arXiv]에 게시한 ‘Flow Equivariant Recurrent Neural Networks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Time-Parameterized Symmetries

[논문리뷰] Flow Equivariant Recurrent Neural Networks

August 3, 2025

T. Anderson Keller이 [arXiv]에 게시한 ‘Flow Equivariant Recurrent Neural Networks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Joint Optimization

[논문리뷰] NeRF Is a Valuable Assistant for 3D Gaussian Splatting

August 3, 2025

ZeSheng Wang이 [arXiv]에 게시한 ‘NeRF Is a Valuable Assistant for 3D Gaussian Splatting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Neural Rendering

[논문리뷰] NeRF Is a Valuable Assistant for 3D Gaussian Splatting

August 3, 2025

ZeSheng Wang이 [arXiv]에 게시한 ‘NeRF Is a Valuable Assistant for 3D Gaussian Splatting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Softmax Attention

[논문리뷰] On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective

August 3, 2025

Eric C. Larson이 [arXiv]에 게시한 ‘On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Recurrent Neural Networks (RNNs)

[논문리뷰] On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective

August 3, 2025

Eric C. Larson이 [arXiv]에 게시한 ‘On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Taylor Series Expansion

[논문리뷰] On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective

August 3, 2025

Eric C. Larson이 [arXiv]에 게시한 ‘On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Expressiveness

[논문리뷰] On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective

August 3, 2025

Eric C. Larson이 [arXiv]에 게시한 ‘On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Persona Control

[논문리뷰] Persona Vectors: Monitoring and Controlling Character Traits in Language Models

August 3, 2025

Jack Lindsey이 [arXiv]에 게시한 ‘Persona Vectors: Monitoring and Controlling Character Traits in Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Activation Steering

[논문리뷰] Persona Vectors: Monitoring and Controlling Character Traits in Language Models

August 3, 2025

Jack Lindsey이 [arXiv]에 게시한 ‘Persona Vectors: Monitoring and Controlling Character Traits in Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Finetuning

[논문리뷰] Persona Vectors: Monitoring and Controlling Character Traits in Language Models

August 3, 2025

Jack Lindsey이 [arXiv]에 게시한 ‘Persona Vectors: Monitoring and Controlling Character Traits in Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Behavioral Shift Detection

[논문리뷰] Persona Vectors: Monitoring and Controlling Character Traits in Language Models

August 3, 2025

Jack Lindsey이 [arXiv]에 게시한 ‘Persona Vectors: Monitoring and Controlling Character Traits in Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Filtering

[논문리뷰] Persona Vectors: Monitoring and Controlling Character Traits in Language Models

August 3, 2025

Jack Lindsey이 [arXiv]에 게시한 ‘Persona Vectors: Monitoring and Controlling Character Traits in Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GUI grounding

[논문리뷰] Phi-Ground Tech Report: Advancing Perception in GUI Grounding

August 3, 2025

Kai Qiu이 [arXiv]에 게시한 ‘Phi-Ground Tech Report: Advancing Perception in GUI Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AI agent

[논문리뷰] Phi-Ground Tech Report: Advancing Perception in GUI Grounding

August 3, 2025

Kai Qiu이 [arXiv]에 게시한 ‘Phi-Ground Tech Report: Advancing Perception in GUI Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Large Multi-modal Model

[논문리뷰] Phi-Ground Tech Report: Advancing Perception in GUI Grounding

August 3, 2025

Kai Qiu이 [arXiv]에 게시한 ‘Phi-Ground Tech Report: Advancing Perception in GUI Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

User Intent Modeling

[논문리뷰] RecGPT Technical Report

August 3, 2025

Jian Wu이 [arXiv]에 게시한 ‘RecGPT Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Stage Training

[논문리뷰] RecGPT Technical Report

August 3, 2025

Jian Wu이 [arXiv]에 게시한 ‘RecGPT Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

E-commerce

[논문리뷰] RecGPT Technical Report

August 3, 2025

Jian Wu이 [arXiv]에 게시한 ‘RecGPT Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Filter Bubble Mitigation

[논문리뷰] RecGPT Technical Report

August 3, 2025

Jian Wu이 [arXiv]에 게시한 ‘RecGPT Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Matthew Effect

[논문리뷰] RecGPT Technical Report

August 3, 2025

Jian Wu이 [arXiv]에 게시한 ‘RecGPT Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visuomotor Agents

[논문리뷰] Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents

August 3, 2025

Anji Liu이 [arXiv]에 게시한 ‘Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Minecraft

[논문리뷰] Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents

August 3, 2025

Anji Liu이 [arXiv]에 게시한 ‘Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-View Goal Specification

[논문리뷰] Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents

August 3, 2025

Anji Liu이 [arXiv]에 게시한 ‘Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Automated Task Synthesis

[논문리뷰] Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents

August 3, 2025

Anji Liu이 [arXiv]에 게시한 ‘Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Geometry Reasoning

[논문리뷰] Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving

August 3, 2025

Zhicheng Jiang이 [arXiv]에 게시한 ‘Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Lemma-Style Proving

[논문리뷰] Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving

August 3, 2025

Zhicheng Jiang이 [arXiv]에 게시한 ‘Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hallucination Reduction

[논문리뷰] TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs

August 3, 2025

Jiasheng Tang이 [arXiv]에 게시한 ‘TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Min-Max Optimization

[논문리뷰] TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs

August 3, 2025

Jiasheng Tang이 [arXiv]에 게시한 ‘TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Token-Adaptive Strategy

[논문리뷰] TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs

August 3, 2025

Jiasheng Tang이 [arXiv]에 게시한 ‘TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spectral Regularization

[논문리뷰] TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs

August 3, 2025

Jiasheng Tang이 [arXiv]에 게시한 ‘TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Feed-forward Models

[논문리뷰] iLRM: An Iterative Large 3D Reconstruction Model

August 3, 2025

Abdelrahman Mohamed이 [arXiv]에 게시한 ‘iLRM: An Iterative Large 3D Reconstruction Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Latent Actions

[논문리뷰] villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models

August 3, 2025

Kaixin Wang이 [arXiv]에 게시한 ‘villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Proprioceptive Feedback

[논문리뷰] villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models

August 3, 2025

Kaixin Wang이 [arXiv]에 게시한 ‘villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Vision-Language Models

[논문리뷰] 3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

August 4, 2025

Hao Tang이 [arXiv]에 게시한 ‘3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scene Understanding

[논문리뷰] 3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

August 4, 2025

Hao Tang이 [arXiv]에 게시한 ‘3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dynamic View Selection

[논문리뷰] 3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

August 4, 2025

Hao Tang이 [arXiv]에 게시한 ‘3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Diffusion Large Language Models

[논문리뷰] Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models

August 4, 2025

Jiaqi Wang이 [arXiv]에 게시한 ‘Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Variable-Length Generation

[논문리뷰] Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models

August 4, 2025

Jiaqi Wang이 [arXiv]에 게시한 ‘Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dynamic Length Adaptation

[논문리뷰] Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models

August 4, 2025

Jiaqi Wang이 [arXiv]에 게시한 ‘Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Denoising Strategy

[논문리뷰] Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models

August 4, 2025

Jiaqi Wang이 [arXiv]에 게시한 ‘Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image-goal Navigation

[논문리뷰] IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation

August 4, 2025

Jianjiang Feng이 [arXiv]에 게시한 ‘IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Incremental Scene Representation

[논문리뷰] IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation

August 4, 2025

Jianjiang Feng이 [arXiv]에 게시한 ‘IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Coarse-to-fine Localization

[논문리뷰] IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation

August 4, 2025

Jianjiang Feng이 [arXiv]에 게시한 ‘IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Differentiable Rendering

[논문리뷰] IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation

August 4, 2025

Jianjiang Feng이 [arXiv]에 게시한 ‘IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Hallucination

[논문리뷰] Investigating Hallucination in Conversations for Low Resource Languages

August 4, 2025

Fatemeh Jamshidi이 [arXiv]에 게시한 ‘Investigating Hallucination in Conversations for Low Resource Languages’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Low-resource Languages

[논문리뷰] Investigating Hallucination in Conversations for Low Resource Languages

August 4, 2025

Fatemeh Jamshidi이 [arXiv]에 게시한 ‘Investigating Hallucination in Conversations for Low Resource Languages’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

ROUGE Score

[논문리뷰] Investigating Hallucination in Conversations for Low Resource Languages

August 4, 2025

Fatemeh Jamshidi이 [arXiv]에 게시한 ‘Investigating Hallucination in Conversations for Low Resource Languages’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-lingual Evaluation

[논문리뷰] Investigating Hallucination in Conversations for Low Resource Languages

August 4, 2025

Fatemeh Jamshidi이 [arXiv]에 게시한 ‘Investigating Hallucination in Conversations for Low Resource Languages’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Factual Consistency

[논문리뷰] Investigating Hallucination in Conversations for Low Resource Languages

August 4, 2025

Fatemeh Jamshidi이 [arXiv]에 게시한 ‘Investigating Hallucination in Conversations for Low Resource Languages’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Turn Dialogue Evaluation

[논문리뷰] Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges

August 4, 2025

Chengfei Lv이 [arXiv]에 게시한 ‘Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Judge Aggregation

[논문리뷰] Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges

August 4, 2025

Chengfei Lv이 [arXiv]에 게시한 ‘Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dialogue Quality Assessment

[논문리뷰] Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges

August 4, 2025

Chengfei Lv이 [arXiv]에 게시한 ‘Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Maximum Likelihood Estimation

[논문리뷰] Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges

August 4, 2025

Chengfei Lv이 [arXiv]에 게시한 ‘Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Referring Segmentation

[논문리뷰] Multimodal Referring Segmentation: A Survey

August 4, 2025

Zuxuan Wu이 [arXiv]에 게시한 ‘Multimodal Referring Segmentation: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image Segmentation

[논문리뷰] Multimodal Referring Segmentation: A Survey

August 4, 2025

Zuxuan Wu이 [arXiv]에 게시한 ‘Multimodal Referring Segmentation: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Neural Fields

[논문리뷰] PixNerd: Pixel Neural Field Diffusion

August 4, 2025

Limin Wang이 [arXiv]에 게시한 ‘PixNerd: Pixel Neural Field Diffusion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pixel Space

[논문리뷰] PixNerd: Pixel Neural Field Diffusion

August 4, 2025

Limin Wang이 [arXiv]에 게시한 ‘PixNerd: Pixel Neural Field Diffusion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fault Localization

[논문리뷰] SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution

August 4, 2025

Heng Lian이 [arXiv]에 게시한 ‘SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Issue Resolution

[논문리뷰] SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution

August 4, 2025

Heng Lian이 [arXiv]에 게시한 ‘SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Competitive Debate

[논문리뷰] SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution

August 4, 2025

Heng Lian이 [arXiv]에 게시한 ‘SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Graph Traversal

[논문리뷰] SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution

August 4, 2025

Heng Lian이 [arXiv]에 게시한 ‘SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Software Issue Resolution

[논문리뷰] SWE-Exp: Experience-Driven Software Issue Resolution

August 4, 2025

Heng Lian이 [arXiv]에 게시한 ‘SWE-Exp: Experience-Driven Software Issue Resolution’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Experience-Driven Learning

[논문리뷰] SWE-Exp: Experience-Driven Software Issue Resolution

August 4, 2025

Heng Lian이 [arXiv]에 게시한 ‘SWE-Exp: Experience-Driven Software Issue Resolution’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Automated Program Repair

[논문리뷰] SWE-Exp: Experience-Driven Software Issue Resolution

August 4, 2025

Heng Lian이 [arXiv]에 게시한 ‘SWE-Exp: Experience-Driven Software Issue Resolution’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Knowledge Management

[논문리뷰] SWE-Exp: Experience-Driven Software Issue Resolution

August 4, 2025

Heng Lian이 [arXiv]에 게시한 ‘SWE-Exp: Experience-Driven Software Issue Resolution’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Continuous Learning

[논문리뷰] SWE-Exp: Experience-Driven Software Issue Resolution

August 4, 2025

Heng Lian이 [arXiv]에 게시한 ‘SWE-Exp: Experience-Driven Software Issue Resolution’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Audio-driven Video Generation

[논문리뷰] SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation

August 4, 2025

Long Chen이 [arXiv]에 게시한 ‘SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spatial Auditory Cues

[논문리뷰] SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation

August 4, 2025

Long Chen이 [arXiv]에 게시한 ‘SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Scene Layout

[논문리뷰] SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation

August 4, 2025

Long Chen이 [arXiv]에 게시한 ‘SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Large Vision-Language Models (LVLMs)

[논문리뷰] A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models

August 5, 2025

Zuxuan Wu이 [arXiv]에 게시한 ‘A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Token Pruning

[논문리뷰] A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models

August 5, 2025

Zuxuan Wu이 [arXiv]에 게시한 ‘A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dynamic Compression

[논문리뷰] A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models

August 5, 2025

Zuxuan Wu이 [arXiv]에 게시한 ‘A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GlimpsePrune

[논문리뷰] A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models

August 5, 2025

Zuxuan Wu이 [arXiv]에 게시한 ‘A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Compute Optimization

[논문리뷰] AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks

August 5, 2025

Zhiwei Zhang이 [arXiv]에 게시한 ‘AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-stage Tasks

[논문리뷰] AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks

August 5, 2025

Zhiwei Zhang이 [arXiv]에 게시한 ‘AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Search Efficiency

[논문리뷰] AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks

August 5, 2025

Zhiwei Zhang이 [arXiv]에 게시한 ‘AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Supervised RL

[논문리뷰] Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models’ Instruction Following

August 5, 2025

Jiaqing Liang이 [arXiv]에 게시한 ‘Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models’ Instruction Following’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AI Scientist

[논문리뷰] CellForge: Agentic Design of Virtual Cell Models

August 5, 2025

Daniel Shao이 [arXiv]에 게시한 ‘CellForge: Agentic Design of Virtual Cell Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Virtual Cell Modeling

[논문리뷰] CellForge: Agentic Design of Virtual Cell Models

August 5, 2025

Daniel Shao이 [arXiv]에 게시한 ‘CellForge: Agentic Design of Virtual Cell Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Single-Cell Perturbation Prediction

[논문리뷰] CellForge: Agentic Design of Virtual Cell Models

August 5, 2025

Daniel Shao이 [arXiv]에 게시한 ‘CellForge: Agentic Design of Virtual Cell Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Automated Model Design

[논문리뷰] CellForge: Agentic Design of Virtual Cell Models

August 5, 2025

Daniel Shao이 [arXiv]에 게시한 ‘CellForge: Agentic Design of Virtual Cell Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cybersecurity Agents

[논문리뷰] Cyber-Zero: Training Cybersecurity Agents without Runtime

August 5, 2025

Zijian Wang이 [arXiv]에 게시한 ‘Cyber-Zero: Training Cybersecurity Agents without Runtime’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Trajectory Synthesis

[논문리뷰] Cyber-Zero: Training Cybersecurity Agents without Runtime

August 5, 2025

Zijian Wang이 [arXiv]에 게시한 ‘Cyber-Zero: Training Cybersecurity Agents without Runtime’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Runtime-Free Training

[논문리뷰] Cyber-Zero: Training Cybersecurity Agents without Runtime

August 5, 2025

Zijian Wang이 [arXiv]에 게시한 ‘Cyber-Zero: Training Cybersecurity Agents without Runtime’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Simulation

[논문리뷰] Cyber-Zero: Training Cybersecurity Agents without Runtime

August 5, 2025

Zijian Wang이 [arXiv]에 게시한 ‘Cyber-Zero: Training Cybersecurity Agents without Runtime’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Meta-RL

[논문리뷰] Exploitation Is All You Need… for Exploration

August 5, 2025

Jesse Roberts이 [arXiv]에 게시한 ‘Exploitation Is All You Need… for Exploration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Emergent Behavior

[논문리뷰] Exploitation Is All You Need… for Exploration

August 5, 2025

Jesse Roberts이 [arXiv]에 게시한 ‘Exploitation Is All You Need… for Exploration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Armed Bandits

[논문리뷰] Exploitation Is All You Need… for Exploration

August 5, 2025

Jesse Roberts이 [arXiv]에 게시한 ‘Exploitation Is All You Need… for Exploration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gridworlds

[논문리뷰] Exploitation Is All You Need… for Exploration

August 5, 2025

Jesse Roberts이 [arXiv]에 게시한 ‘Exploitation Is All You Need… for Exploration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pseudo-Thompson Sampling

[논문리뷰] Exploitation Is All You Need… for Exploration

August 5, 2025

Jesse Roberts이 [arXiv]에 게시한 ‘Exploitation Is All You Need… for Exploration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cyber Threat Intelligence

[논문리뷰] Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report

August 5, 2025

Anu Vellore이 [arXiv]에 게시한 ‘Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Chatbot

[논문리뷰] Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report

August 5, 2025

Anu Vellore이 [arXiv]에 게시한 ‘Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Personalized Safety Alignment

[논문리뷰] Personalized Safety Alignment for Text-to-Image Diffusion Models

August 5, 2025

Kaidong Yu이 [arXiv]에 게시한 ‘Personalized Safety Alignment for Text-to-Image Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-to-Image Diffusion Models

[논문리뷰] Personalized Safety Alignment for Text-to-Image Diffusion Models

August 5, 2025

Kaidong Yu이 [arXiv]에 게시한 ‘Personalized Safety Alignment for Text-to-Image Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

User Preferences

[논문리뷰] Personalized Safety Alignment for Text-to-Image Diffusion Models

August 5, 2025

Kaidong Yu이 [arXiv]에 게시한 ‘Personalized Safety Alignment for Text-to-Image Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text Rendering

[논문리뷰] Qwen-Image Technical Report

August 5, 2025

Kaiyuan Gao이 [arXiv]에 게시한 ‘Qwen-Image Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Diffusion Transformer

[논문리뷰] Qwen-Image Technical Report

August 5, 2025

Kaiyuan Gao이 [arXiv]에 게시한 ‘Qwen-Image Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-memory Systems

[논문리뷰] RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Lifelong Learning in Physical Embodied Systems

August 5, 2025

Junkun Hong이 [arXiv]에 게시한 ‘RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Lifelong Learning in Physical Embodied Systems’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Knowledge Graph

[논문리뷰] RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Lifelong Learning in Physical Embodied Systems

August 5, 2025

Junkun Hong이 [arXiv]에 게시한 ‘RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Lifelong Learning in Physical Embodied Systems’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Closed-Loop Planning

[논문리뷰] RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Lifelong Learning in Physical Embodied Systems

August 5, 2025

Junkun Hong이 [arXiv]에 게시한 ‘RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Lifelong Learning in Physical Embodied Systems’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Context-Aware Embedding

[논문리뷰] SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension

August 5, 2025

Liyan Xu이 [arXiv]에 게시한 ‘SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long Document Comprehension

[논문리뷰] SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension

August 5, 2025

Liyan Xu이 [arXiv]에 게시한 ‘SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semantic Association

[논문리뷰] SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension

August 5, 2025

Liyan Xu이 [arXiv]에 게시한 ‘SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text Embedding

[논문리뷰] SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension

August 5, 2025

Liyan Xu이 [arXiv]에 게시한 ‘SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Omni-modal LLMs

[논문리뷰] VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

August 5, 2025

Bin Jia이 [arXiv]에 게시한 ‘VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Distributed Training

[논문리뷰] VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

August 5, 2025

Bin Jia이 [arXiv]에 게시한 ‘VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model-centric

[논문리뷰] VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

August 5, 2025

Bin Jia이 [arXiv]에 게시한 ‘VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Parallelism

[논문리뷰] VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

August 5, 2025

Bin Jia이 [arXiv]에 게시한 ‘VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

FSDP

[논문리뷰] VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

August 5, 2025

Bin Jia이 [arXiv]에 게시한 ‘VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sequence Parallelism

[논문리뷰] VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

August 5, 2025

Bin Jia이 [arXiv]에 게시한 ‘VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Expert Parallelism

[논문리뷰] VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

August 5, 2025

Bin Jia이 [arXiv]에 게시한 ‘VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Alignment Preservation

[논문리뷰] AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization

August 6, 2025

Aman Chadha이 [arXiv]에 게시한 ‘AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization...

Back to Top ↑

Fisher Information Matrix

[논문리뷰] AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization

August 6, 2025

Aman Chadha이 [arXiv]에 게시한 ‘AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization...

Back to Top ↑

Riemannian Geometry

[논문리뷰] AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization

August 6, 2025

Aman Chadha이 [arXiv]에 게시한 ‘AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization...

Back to Top ↑

Approximate Nearest Neighbor Search

[논문리뷰] CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search

August 6, 2025

Jiwei Li이 [arXiv]에 게시한 ‘CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Code Optimization

[논문리뷰] CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search

August 6, 2025

Jiwei Li이 [arXiv]에 게시한 ‘CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

HNSW

[논문리뷰] CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search

August 6, 2025

Jiwei Li이 [arXiv]에 게시한 ‘CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Chart Captioning

[논문리뷰] ChartCap: Mitigating Hallucination of Dense Chart Captioning

August 6, 2025

Gunhee Kim이 [arXiv]에 게시한 ‘ChartCap: Mitigating Hallucination of Dense Chart Captioning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cycle Consistency

[논문리뷰] ChartCap: Mitigating Hallucination of Dense Chart Captioning

August 6, 2025

Gunhee Kim이 [arXiv]에 게시한 ‘ChartCap: Mitigating Hallucination of Dense Chart Captioning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reference-Free Metric

[논문리뷰] ChartCap: Mitigating Hallucination of Dense Chart Captioning

August 6, 2025

Gunhee Kim이 [arXiv]에 게시한 ‘ChartCap: Mitigating Hallucination of Dense Chart Captioning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Answer Verification

[논문리뷰] CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward

August 6, 2025

Songyang Gao이 [arXiv]에 게시한 ‘CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Formula Verification

[논문리뷰] CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward

August 6, 2025

Songyang Gao이 [arXiv]에 게시한 ‘CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Averaging

[논문리뷰] Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction

August 6, 2025

Jui-Hui Chung이 [arXiv]에 게시한 ‘Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Image Composition

[논문리뷰] LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer

August 6, 2025

Shunyu Yao이 [arXiv]에 게시한 ‘LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Layout Control

[논문리뷰] LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer

August 6, 2025

Shunyu Yao이 [arXiv]에 게시한 ‘LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Tool-use

[논문리뷰] LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?

August 6, 2025

Yaojie Lu이 [arXiv]에 게시한 ‘LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

MCP

[논문리뷰] LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?

August 6, 2025

Yaojie Lu이 [arXiv]에 게시한 ‘LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Large-scale

[논문리뷰] LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?

August 6, 2025

Yaojie Lu이 [arXiv]에 게시한 ‘LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-world tasks

[논문리뷰] LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?

August 6, 2025

Yaojie Lu이 [arXiv]에 게시한 ‘LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Meta-tool-learning

[논문리뷰] LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?

August 6, 2025

Yaojie Lu이 [arXiv]에 게시한 ‘LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Ultra-long Video Generation

[논문리뷰] LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation

August 6, 2025

Chenyang Si이 [arXiv]에 게시한 ‘LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Guidance

[논문리뷰] LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation

August 6, 2025

Chenyang Si이 [arXiv]에 게시한 ‘LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Controllable Video Generation

[논문리뷰] LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation

August 6, 2025

Chenyang Si이 [arXiv]에 게시한 ‘LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Degradation-aware Training

[논문리뷰] LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation

August 6, 2025

Chenyang Si이 [arXiv]에 게시한 ‘LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-human Video Generation

[논문리뷰] Multi-human Interactive Talking Dataset

August 6, 2025

Mike Zheng Shou이 [arXiv]에 게시한 ‘Multi-human Interactive Talking Dataset’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Interactive Talking

[논문리뷰] Multi-human Interactive Talking Dataset

August 6, 2025

Mike Zheng Shou이 [arXiv]에 게시한 ‘Multi-human Interactive Talking Dataset’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Audio-driven Animation

[논문리뷰] Multi-human Interactive Talking Dataset

August 6, 2025

Mike Zheng Shou이 [arXiv]에 게시한 ‘Multi-human Interactive Talking Dataset’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Speech Interaction

[논문리뷰] Multi-human Interactive Talking Dataset

August 6, 2025

Mike Zheng Shou이 [arXiv]에 게시한 ‘Multi-human Interactive Talking Dataset’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Non-Autoregressive Inference

[논문리뷰] Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

August 6, 2025

Fan Xia이 [arXiv]에 게시한 ‘Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

High-Speed Inference

[논문리뷰] Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

August 6, 2025

Fan Xia이 [arXiv]에 게시한 ‘Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Alignment Drift

[논문리뷰] TRACEALIGN – Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs

August 6, 2025

Aman Chadha이 [arXiv]에 게시한 ‘TRACEALIGN – Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Training Data Provenance

[논문리뷰] TRACEALIGN – Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs

August 6, 2025

Aman Chadha이 [arXiv]에 게시한 ‘TRACEALIGN – Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Belief Conflict Index (BCI)

[논문리뷰] TRACEALIGN – Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs

August 6, 2025

Aman Chadha이 [arXiv]에 게시한 ‘TRACEALIGN – Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Suffix Array

[논문리뷰] TRACEALIGN – Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs

August 6, 2025

Aman Chadha이 [arXiv]에 게시한 ‘TRACEALIGN – Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Safety Interventions

[논문리뷰] TRACEALIGN – Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs

August 6, 2025

Aman Chadha이 [arXiv]에 게시한 ‘TRACEALIGN – Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Issue Localization

[논문리뷰] Tool-integrated Reinforcement Learning for Repo Deep Search

August 6, 2025

Yanzhen Zou이 [arXiv]에 게시한 ‘Tool-integrated Reinforcement Learning for Repo Deep Search’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Tool-integrated Agents

[논문리뷰] Tool-integrated Reinforcement Learning for Repo Deep Search

August 6, 2025

Yanzhen Zou이 [arXiv]에 게시한 ‘Tool-integrated Reinforcement Learning for Repo Deep Search’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Code Search

[논문리뷰] Tool-integrated Reinforcement Learning for Repo Deep Search

August 6, 2025

Yanzhen Zou이 [arXiv]에 게시한 ‘Tool-integrated Reinforcement Learning for Repo Deep Search’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Occupancy Grounding

[논문리뷰] A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding

August 7, 2025

Jianke Zhu이 [arXiv]에 게시한 ‘A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Voxel-based Prediction

[논문리뷰] A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding

August 7, 2025

Jianke Zhu이 [arXiv]에 게시한 ‘A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Coarse-to-Fine

[논문리뷰] A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding

August 7, 2025

Jianke Zhu이 [arXiv]에 게시한 ‘A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hierarchical RL

[논문리뷰] Agent Lightning: Train ANY AI Agents with Reinforcement Learning

August 7, 2025

Zilong Wang이 [arXiv]에 게시한 ‘Agent Lightning: Train ANY AI Agents with Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Training-Agent Disaggregation

[논문리뷰] Agent Lightning: Train ANY AI Agents with Reinforcement Learning

August 7, 2025

Zilong Wang이 [arXiv]에 게시한 ‘Agent Lightning: Train ANY AI Agents with Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Observability

[논문리뷰] Agent Lightning: Train ANY AI Agents with Reinforcement Learning

August 7, 2025

Zilong Wang이 [arXiv]에 게시한 ‘Agent Lightning: Train ANY AI Agents with Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Anomaly Detection

[논문리뷰] C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor

August 7, 2025

Jinbao Wang이 [arXiv]에 게시한 ‘C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Kernel Attention

[논문리뷰] C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor

August 7, 2025

Jinbao Wang이 [arXiv]에 게시한 ‘C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Learnable Advisor

[논문리뷰] C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor

August 7, 2025

Jinbao Wang이 [arXiv]에 게시한 ‘C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Parameter Perturbation

[논문리뷰] C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor

August 7, 2025

Jinbao Wang이 [arXiv]에 게시한 ‘C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Point Cloud

[논문리뷰] C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor

August 7, 2025

Jinbao Wang이 [arXiv]에 게시한 ‘C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Industrial AI

[논문리뷰] C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor

August 7, 2025

Jinbao Wang이 [arXiv]에 게시한 ‘C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Toxicity Prediction

[논문리뷰] CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction

August 7, 2025

Donghyeon Lee이 [arXiv]에 게시한 ‘CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Drug Development

[논문리뷰] CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction

August 7, 2025

Donghyeon Lee이 [arXiv]에 게시한 ‘CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cheminformatics

[논문리뷰] CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction

August 7, 2025

Donghyeon Lee이 [arXiv]에 게시한 ‘CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Interpretable AI

[논문리뷰] CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction

August 7, 2025

Donghyeon Lee이 [arXiv]에 게시한 ‘CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

IUPAC Nomenclature

[논문리뷰] CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction

August 7, 2025

Donghyeon Lee이 [arXiv]에 게시한 ‘CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Virtual Try-On

[논문리뷰] DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework

August 7, 2025

Chao Liang이 [arXiv]에 게시한 ‘DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Stage-Wise Framework

[논문리뷰] DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework

August 7, 2025

Chao Liang이 [arXiv]에 게시한 ‘DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Garment Preservation

[논문리뷰] DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework

August 7, 2025

Chao Liang이 [arXiv]에 게시한 ‘DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

C-to-Rust Conversion

[논문리뷰] EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation

August 7, 2025

Dong Chen이 [arXiv]에 게시한 ‘EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Project-Level Translation

[논문리뷰] EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation

August 7, 2025

Dong Chen이 [arXiv]에 게시한 ‘EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Code Synthesis

[논문리뷰] EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation

August 7, 2025

Dong Chen이 [arXiv]에 게시한 ‘EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Memory Safety

[논문리뷰] EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation

August 7, 2025

Dong Chen이 [arXiv]에 게시한 ‘EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Software Migration

[논문리뷰] EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation

August 7, 2025

Dong Chen이 [arXiv]에 게시한 ‘EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hybrid Translation

[논문리뷰] EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation

August 7, 2025

Dong Chen이 [arXiv]에 게시한 ‘EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cost Efficiency

[논문리뷰] Efficient Agents: Building Effective Agents While Reducing Cost

August 7, 2025

Yue Hou이 [arXiv]에 게시한 ‘Efficient Agents: Building Effective Agents While Reducing Cost’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Performance-Cost Trade-off

[논문리뷰] Efficient Agents: Building Effective Agents While Reducing Cost

August 7, 2025

Yue Hou이 [arXiv]에 게시한 ‘Efficient Agents: Building Effective Agents While Reducing Cost’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Synthetic Worlds

[논문리뷰] Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success

August 7, 2025

Ruslan Rakhimov이 [arXiv]에 게시한 ‘Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success’ 논문에 대한 자세한 리뷰...

Back to Top ↑

Transfer Learning

[논문리뷰] Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success

August 7, 2025

Ruslan Rakhimov이 [arXiv]에 게시한 ‘Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success’ 논문에 대한 자세한 리뷰...

Back to Top ↑

Video-to-3D Synthesis

[논문리뷰] Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

August 7, 2025

Feng Zhao이 [arXiv]에 게시한 ‘Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Latent Space Modeling

[논문리뷰] Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

August 7, 2025

Feng Zhao이 [arXiv]에 게시한 ‘Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Temporal Coherence

[논문리뷰] Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

August 7, 2025

Feng Zhao이 [arXiv]에 게시한 ‘Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human Preference Score

[논문리뷰] HPSv3: Towards Wide-Spectrum Human Preference Score

August 7, 2025

Hongsheng Li이 [arXiv]에 게시한 ‘HPSv3: Towards Wide-Spectrum Human Preference Score’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image Evaluation

[논문리뷰] HPSv3: Towards Wide-Spectrum Human Preference Score

August 7, 2025

Hongsheng Li이 [arXiv]에 게시한 ‘HPSv3: Towards Wide-Spectrum Human Preference Score’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Uncertainty-Aware Ranking Loss

[논문리뷰] HPSv3: Towards Wide-Spectrum Human Preference Score

August 7, 2025

Hongsheng Li이 [arXiv]에 게시한 ‘HPSv3: Towards Wide-Spectrum Human Preference Score’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Query-based Model

[논문리뷰] IAUNet: Instance-Aware U-Net

August 7, 2025

Dmytro Fishman이 [arXiv]에 게시한 ‘IAUNet: Instance-Aware U-Net’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Transformer Decoder

[논문리뷰] IAUNet: Instance-Aware U-Net

August 7, 2025

Dmytro Fishman이 [arXiv]에 게시한 ‘IAUNet: Instance-Aware U-Net’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Biomedical Imaging

[논문리뷰] IAUNet: Instance-Aware U-Net

August 7, 2025

Dmytro Fishman이 [arXiv]에 게시한 ‘IAUNet: Instance-Aware U-Net’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cell Segmentation

[논문리뷰] IAUNet: Instance-Aware U-Net

August 7, 2025

Dmytro Fishman이 [arXiv]에 게시한 ‘IAUNet: Instance-Aware U-Net’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

OOD Generalization

[논문리뷰] Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens

August 7, 2025

Zhen Tan이 [arXiv]에 게시한 ‘Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Distribution Shift

[논문리뷰] Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens

August 7, 2025

Zhen Tan이 [arXiv]에 게시한 ‘Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pattern Matching

[논문리뷰] Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens

August 7, 2025

Zhen Tan이 [arXiv]에 게시한 ‘Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

DataAlchemy

[논문리뷰] Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens

August 7, 2025

Zhen Tan이 [arXiv]에 게시한 ‘Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Design-to-Code

[논문리뷰] LaTCoder: Converting Webpage Design to Code with Layout-as-Thought

August 7, 2025

Tianpeng Lv이 [arXiv]에 게시한 ‘LaTCoder: Converting Webpage Design to Code with Layout-as-Thought’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Webpage Generation

[논문리뷰] LaTCoder: Converting Webpage Design to Code with Layout-as-Thought

August 7, 2025

Tianpeng Lv이 [arXiv]에 게시한 ‘LaTCoder: Converting Webpage Design to Code with Layout-as-Thought’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Layout Preservation

[논문리뷰] LaTCoder: Converting Webpage Design to Code with Layout-as-Thought

August 7, 2025

Tianpeng Lv이 [arXiv]에 게시한 ‘LaTCoder: Converting Webpage Design to Code with Layout-as-Thought’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Efficient Decoding

[논문리뷰] LeanK: Learnable K Cache Channel Pruning for Efficient Decoding

August 7, 2025

Yuqing Yang이 [arXiv]에 게시한 ‘LeanK: Learnable K Cache Channel Pruning for Efficient Decoding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Static Sparsity

[논문리뷰] LeanK: Learnable K Cache Channel Pruning for Efficient Decoding

August 7, 2025

Yuqing Yang이 [arXiv]에 게시한 ‘LeanK: Learnable K Cache Channel Pruning for Efficient Decoding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Entropy Regularization

[논문리뷰] Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following

August 7, 2025

Liang Xu이 [arXiv]에 게시한 ‘Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Checking

[논문리뷰] Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following

August 7, 2025

Liang Xu이 [arXiv]에 게시한 ‘Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Previewing

[논문리뷰] Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following

August 7, 2025

Liang Xu이 [arXiv]에 게시한 ‘Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Audio-Language Model

[논문리뷰] MiDashengLM: Efficient Audio Understanding with General Audio Captions

August 7, 2025

Yadong Niu이 [arXiv]에 게시한 ‘MiDashengLM: Efficient Audio Understanding with General Audio Captions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

General Audio Captions

[논문리뷰] MiDashengLM: Efficient Audio Understanding with General Audio Captions

August 7, 2025

Yadong Niu이 [arXiv]에 게시한 ‘MiDashengLM: Efficient Audio Understanding with General Audio Captions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Public Datasets

[논문리뷰] MiDashengLM: Efficient Audio Understanding with General Audio Captions

August 7, 2025

Yadong Niu이 [arXiv]에 게시한 ‘MiDashengLM: Efficient Audio Understanding with General Audio Captions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Biomedical NER

[논문리뷰] OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets

August 7, 2025

MaziyarPanahi이 [arXiv]에 게시한 ‘OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets’ 논문에 대한 자세한 ...

Back to Top ↑

Named Entity Recognition

[논문리뷰] OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets

August 7, 2025

MaziyarPanahi이 [arXiv]에 게시한 ‘OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets’ 논문에 대한 자세한 ...

Back to Top ↑

Healthcare AI

[논문리뷰] OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets

August 7, 2025

MaziyarPanahi이 [arXiv]에 게시한 ‘OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets’ 논문에 대한 자세한 ...

Back to Top ↑

AI Conferences

[논문리뷰] Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference

August 7, 2025

Jiaying Wu이 [arXiv]에 게시한 ‘Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sustainability

[논문리뷰] Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference

August 7, 2025

Jiaying Wu이 [arXiv]에 게시한 ‘Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Community Building

[논문리뷰] Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference

August 7, 2025

Jiaying Wu이 [arXiv]에 게시한 ‘Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Environmental Impact

[논문리뷰] Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference

August 7, 2025

Jiaying Wu이 [arXiv]에 게시한 ‘Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mental Health

[논문리뷰] Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference

August 7, 2025

Jiaying Wu이 [arXiv]에 게시한 ‘Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Centralized Model

[논문리뷰] Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference

August 7, 2025

Jiaying Wu이 [arXiv]에 게시한 ‘Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Decentralized Model

[논문리뷰] Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference

August 7, 2025

Jiaying Wu이 [arXiv]에 게시한 ‘Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Capability Collapse

[논문리뷰] RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization

August 7, 2025

Kechi Zhang이 [arXiv]에 게시한 ‘RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization’ 논문에 대한 자세한 리뷰입...

Back to Top ↑

Hybrid Policy Optimization

[논문리뷰] RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization

August 7, 2025

Kechi Zhang이 [arXiv]에 게시한 ‘RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization’ 논문에 대한 자세한 리뷰입...

Back to Top ↑

Multiple Importance Sampling

[논문리뷰] RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization

August 7, 2025

Kechi Zhang이 [arXiv]에 게시한 ‘RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization’ 논문에 대한 자세한 리뷰입...

Back to Top ↑

Root Cause Analysis

[논문리뷰] Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks

August 7, 2025

Haozhe Zhang이 [arXiv]에 게시한 ‘Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

5G Wireless Networks

[논문리뷰] Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks

August 7, 2025

Haozhe Zhang이 [arXiv]에 게시한 ‘Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

TeleLogs Dataset

[논문리뷰] Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks

August 7, 2025

Haozhe Zhang이 [arXiv]에 게시한 ‘Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Evolving

[논문리뷰] SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience

August 7, 2025

Xiaoyi Dong이 [arXiv]에 게시한 ‘SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Experiential Learning

[논문리뷰] SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience

August 7, 2025

Xiaoyi Dong이 [arXiv]에 게시한 ‘SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Specialist-to-Generalist

[논문리뷰] SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience

August 7, 2025

Xiaoyi Dong이 [arXiv]에 게시한 ‘SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Active Context Management

[논문리뷰] Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management

August 7, 2025

Yunxin Liu이 [arXiv]에 게시한 ‘Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Proactive Interference

[논문리뷰] Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management

August 7, 2025

Yunxin Liu이 [arXiv]에 게시한 ‘Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Tool Augmentation

[논문리뷰] Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management

August 7, 2025

Yunxin Liu이 [arXiv]에 게시한 ‘Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Working Memory

[논문리뷰] Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management

August 7, 2025

Yunxin Liu이 [arXiv]에 게시한 ‘Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Context Curation

[논문리뷰] Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management

August 7, 2025

Yunxin Liu이 [arXiv]에 게시한 ‘Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Analytics

[논문리뷰] Sel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generation

August 7, 2025

Hao Huang이 [arXiv]에 게시한 ‘Sel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Model Evaluation

[논문리뷰] Sel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generation

August 7, 2025

Hao Huang이 [arXiv]에 게시한 ‘Sel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Music Restoration

[논문리뷰] SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering

August 7, 2025

Ambuj Mehrish이 [arXiv]에 게시한 ‘SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Audio Mastering

[논문리뷰] SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering

August 7, 2025

Ambuj Mehrish이 [arXiv]에 게시한 ‘SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Audio Quality Enhancement

[논문리뷰] SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering

August 7, 2025

Ambuj Mehrish이 [arXiv]에 게시한 ‘SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Social Intelligence

[논문리뷰] Sotopia-RL: Reward Design for Social Intelligence

August 7, 2025

Keyang Xuan이 [arXiv]에 게시한 ‘Sotopia-RL: Reward Design for Social Intelligence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Utterance-level Rewards

[논문리뷰] Sotopia-RL: Reward Design for Social Intelligence

August 7, 2025

Keyang Xuan이 [arXiv]에 게시한 ‘Sotopia-RL: Reward Design for Social Intelligence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-dimensional Rewards

[논문리뷰] Sotopia-RL: Reward Design for Social Intelligence

August 7, 2025

Keyang Xuan이 [arXiv]에 게시한 ‘Sotopia-RL: Reward Design for Social Intelligence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Partial Observability

[논문리뷰] Sotopia-RL: Reward Design for Social Intelligence

August 7, 2025

Keyang Xuan이 [arXiv]에 게시한 ‘Sotopia-RL: Reward Design for Social Intelligence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

SOTOPIA

[논문리뷰] Sotopia-RL: Reward Design for Social Intelligence

August 7, 2025

Keyang Xuan이 [arXiv]에 게시한 ‘Sotopia-RL: Reward Design for Social Intelligence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-Attention Analysis

[논문리뷰] The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models

August 7, 2025

Elisabetta Rocchetti이 [arXiv]에 게시한 ‘The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Content-Style Disentanglement

[논문리뷰] The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models

August 7, 2025

Elisabetta Rocchetti이 [arXiv]에 게시한 ‘The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Artistic Style Transfer

[논문리뷰] The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models

August 7, 2025

Elisabetta Rocchetti이 [arXiv]에 게시한 ‘The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

SDXL

[논문리뷰] The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models

August 7, 2025

Elisabetta Rocchetti이 [arXiv]에 게시한 ‘The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

DAPO

[논문리뷰] Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning

August 7, 2025

Maksim Nekrashevich이 [arXiv]에 게시한 ‘Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Autonomous Agents

[논문리뷰] Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning

August 7, 2025

Maksim Nekrashevich이 [arXiv]에 게시한 ‘Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

SWE-BENCH

[논문리뷰] Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning

August 7, 2025

Maksim Nekrashevich이 [arXiv]에 게시한 ‘Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Web Agent

[논문리뷰] Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents

August 7, 2025

Xinyu Yang이 [arXiv]에 게시한 ‘Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Knowledge-Induced

[논문리뷰] Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents

August 7, 2025

Xinyu Yang이 [arXiv]에 게시한 ‘Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Large Multimodal Models (LMMs)

[논문리뷰] Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents

August 7, 2025

Xinyu Yang이 [arXiv]에 게시한 ‘Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bloom's Taxonomy

[논문리뷰] Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents

August 7, 2025

Xinyu Yang이 [arXiv]에 게시한 ‘Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Web-CogDataset

[논문리뷰] Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents

August 7, 2025

Xinyu Yang이 [arXiv]에 게시한 ‘Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Web-CogBench

[논문리뷰] Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents

August 7, 2025

Xinyu Yang이 [arXiv]에 게시한 ‘Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Well-being Concepts

[논문리뷰] Are Today’s LLMs Ready to Explain Well-Being Concepts?

August 8, 2025

Huan Liu이 [arXiv]에 게시한 ‘Are Today’s LLMs Ready to Explain Well-Being Concepts?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Principle-Guided Evaluation

[논문리뷰] Are Today’s LLMs Ready to Explain Well-Being Concepts?

August 8, 2025

Huan Liu이 [arXiv]에 게시한 ‘Are Today’s LLMs Ready to Explain Well-Being Concepts?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Explanation Generation

[논문리뷰] Are Today’s LLMs Ready to Explain Well-Being Concepts?

August 8, 2025

Huan Liu이 [arXiv]에 게시한 ‘Are Today’s LLMs Ready to Explain Well-Being Concepts?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-hop Reasoning

[논문리뷰] Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?

August 8, 2025

Junjie Yang이 [arXiv]에 게시한 ‘Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Evaluation Dataset

[논문리뷰] Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?

August 8, 2025

Junjie Yang이 [arXiv]에 게시한 ‘Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Input Scrutiny

[논문리뷰] Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability

August 8, 2025

Yuan Wu이 [arXiv]에 게시한 ‘Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability’ 논문에 대...

Back to Top ↑

Error Detection

[논문리뷰] Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability

August 8, 2025

Yuan Wu이 [arXiv]에 게시한 ‘Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability’ 논문에 대...

Back to Top ↑

Faulty Inputs

[논문리뷰] Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability

August 8, 2025

Yuan Wu이 [arXiv]에 게시한 ‘Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability’ 논문에 대...

Back to Top ↑

Modality Preference

[논문리뷰] Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability

August 8, 2025

Yuan Wu이 [arXiv]에 게시한 ‘Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability’ 논문에 대...

Back to Top ↑

Cross-Modal Inconsistency

[논문리뷰] Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability

August 8, 2025

Yuan Wu이 [arXiv]에 게시한 ‘Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability’ 논문에 대...

Back to Top ↑

AI Agent

[논문리뷰] CoAct-1: Computer-using Agents with Coding as Actions

August 8, 2025

Taiwei Shi이 [arXiv]에 게시한 ‘CoAct-1: Computer-using Agents with Coding as Actions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-agent System

[논문리뷰] CoAct-1: Computer-using Agents with Coding as Actions

August 8, 2025

Taiwei Shi이 [arXiv]에 게시한 ‘CoAct-1: Computer-using Agents with Coding as Actions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Programmatic Control

[논문리뷰] CoAct-1: Computer-using Agents with Coding as Actions

August 8, 2025

Taiwei Shi이 [arXiv]에 게시한 ‘CoAct-1: Computer-using Agents with Coding as Actions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

OSWorld Benchmark

[논문리뷰] CoAct-1: Computer-using Agents with Coding as Actions

August 8, 2025

Taiwei Shi이 [arXiv]에 게시한 ‘CoAct-1: Computer-using Agents with Coding as Actions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hybrid AI

[논문리뷰] CoAct-1: Computer-using Agents with Coding as Actions

August 8, 2025

Taiwei Shi이 [arXiv]에 게시한 ‘CoAct-1: Computer-using Agents with Coding as Actions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vision Language Models (VLMs)

[논문리뷰] DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning

August 8, 2025

Ziming Wang이 [arXiv]에 게시한 ‘DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Physical Reasoning

[논문리뷰] DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning

August 8, 2025

Ziming Wang이 [arXiv]에 게시한 ‘DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Simulation Environments

[논문리뷰] DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning

August 8, 2025

Ziming Wang이 [arXiv]에 게시한 ‘DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Interactive AI

[논문리뷰] DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning

August 8, 2025

Ziming Wang이 [arXiv]에 게시한 ‘DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Efficient Reasoning

[논문리뷰] Don’t Overthink It: A Survey of Efficient R1-style Large Reasoning Models

August 8, 2025

Fangzhou Yao이 [arXiv]에 게시한 ‘Don’t Overthink It: A Survey of Efficient R1-style Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Optimization

[논문리뷰] Don’t Overthink It: A Survey of Efficient R1-style Large Reasoning Models

August 8, 2025

Fangzhou Yao이 [arXiv]에 게시한 ‘Don’t Overthink It: A Survey of Efficient R1-style Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Collaboration

[논문리뷰] Don’t Overthink It: A Survey of Efficient R1-style Large Reasoning Models

August 8, 2025

Fangzhou Yao이 [arXiv]에 게시한 ‘Don’t Overthink It: A Survey of Efficient R1-style Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Overthinking Problem

[논문리뷰] Don’t Overthink It: A Survey of Efficient R1-style Large Reasoning Models

August 8, 2025

Fangzhou Yao이 [arXiv]에 게시한 ‘Don’t Overthink It: A Survey of Efficient R1-style Large Reasoning Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Customer Support

[논문리뷰] Evaluating, Synthesizing, and Enhancing for Customer Support Conversation

August 8, 2025

Feng Chen이 [arXiv]에 게시한 ‘Evaluating, Synthesizing, and Enhancing for Customer Support Conversation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dialogue Generation

[논문리뷰] Evaluating, Synthesizing, and Enhancing for Customer Support Conversation

August 8, 2025

Feng Chen이 [arXiv]에 게시한 ‘Evaluating, Synthesizing, and Enhancing for Customer Support Conversation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Role-Playing

[논문리뷰] Evaluating, Synthesizing, and Enhancing for Customer Support Conversation

August 8, 2025

Feng Chen이 [arXiv]에 게시한 ‘Evaluating, Synthesizing, and Enhancing for Customer Support Conversation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

COPC Framework

[논문리뷰] Evaluating, Synthesizing, and Enhancing for Customer Support Conversation

August 8, 2025

Feng Chen이 [arXiv]에 게시한 ‘Evaluating, Synthesizing, and Enhancing for Customer Support Conversation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Strategy Prediction

[논문리뷰] Evaluating, Synthesizing, and Enhancing for Customer Support Conversation

August 8, 2025

Feng Chen이 [arXiv]에 게시한 ‘Evaluating, Synthesizing, and Enhancing for Customer Support Conversation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Empathetic AI

[논문리뷰] Evaluating, Synthesizing, and Enhancing for Customer Support Conversation

August 8, 2025

Feng Chen이 [arXiv]에 게시한 ‘Evaluating, Synthesizing, and Enhancing for Customer Support Conversation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Policy Learning

[논문리뷰] Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation

August 8, 2025

Shengcong Chen이 [arXiv]에 게시한 ‘Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Generation Evaluation

[논문리뷰] Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity

August 8, 2025

Zhibing Li이 [arXiv]에 게시한 ‘Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hierarchical Evaluation

[논문리뷰] Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity

August 8, 2025

Zhibing Li이 [arXiv]에 게시한 ‘Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Material Properties

[논문리뷰] Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity

August 8, 2025

Zhibing Li이 [arXiv]에 게시한 ‘Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Agent Annotation

[논문리뷰] Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity

August 8, 2025

Zhibing Li이 [arXiv]에 게시한 ‘Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hybrid Scoring System

[논문리뷰] Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity

August 8, 2025

Zhibing Li이 [arXiv]에 게시한 ‘Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video-based Evaluation

[논문리뷰] Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity

August 8, 2025

Zhibing Li이 [arXiv]에 게시한 ‘Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Part-level Analysis

[논문리뷰] Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity

August 8, 2025

Zhibing Li이 [arXiv]에 게시한 ‘Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-hop Question Answering

[논문리뷰] Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis

August 8, 2025

Reshmi Ghosh이 [arXiv]에 게시한 ‘Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning Errors

[논문리뷰] Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis

August 8, 2025

Reshmi Ghosh이 [arXiv]에 게시한 ‘Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Error Taxonomy

[논문리뷰] Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis

August 8, 2025

Reshmi Ghosh이 [arXiv]에 게시한 ‘Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Entity Linking

[논문리뷰] I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking

August 8, 2025

Chao Wang이 [arXiv]에 게시한 ‘I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Collaborative Reflection

[논문리뷰] I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking

August 8, 2025

Chao Wang이 [arXiv]에 게시한 ‘I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Information

[논문리뷰] I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking

August 8, 2025

Chao Wang이 [arXiv]에 게시한 ‘I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-centric

[논문리뷰] I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking

August 8, 2025

Chao Wang이 [arXiv]에 게시한 ‘I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Bias

[논문리뷰] I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations

August 8, 2025

Chirag Shah이 [arXiv]에 게시한 ‘I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations’ 논문에...

Back to Top ↑

Hiring Evaluation

[논문리뷰] I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations

August 8, 2025

Chirag Shah이 [arXiv]에 게시한 ‘I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations’ 논문에...

Back to Top ↑

Linguistic Shibboleth

[논문리뷰] I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations

August 8, 2025

Chirag Shah이 [arXiv]에 게시한 ‘I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations’ 논문에...

Back to Top ↑

Hedging Language

[논문리뷰] I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations

August 8, 2025

Chirag Shah이 [arXiv]에 게시한 ‘I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations’ 논문에...

Back to Top ↑

Sample Efficiency

[논문리뷰] InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities

August 8, 2025

Zhijie Sang이 [arXiv]에 게시한 ‘InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-dimensional Filtering

[논문리뷰] InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities

August 8, 2025

Zhijie Sang이 [arXiv]에 게시한 ‘InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Object Segmentation

[논문리뷰] MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes

August 8, 2025

Xudong Jiang이 [arXiv]에 게시한 ‘MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Complex Scenes

[논문리뷰] MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes

August 8, 2025

Xudong Jiang이 [arXiv]에 게시한 ‘MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Object Tracking

[논문리뷰] MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes

August 8, 2025

Xudong Jiang이 [arXiv]에 게시한 ‘MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dataset Challenges

[논문리뷰] MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes

August 8, 2025

Xudong Jiang이 [arXiv]에 게시한 ‘MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Voice Cloning

[논문리뷰] Marco-Voice Technical Report

August 8, 2025

Qingjuan Li이 [arXiv]에 게시한 ‘Marco-Voice Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Emotion Control

[논문리뷰] Marco-Voice Technical Report

August 8, 2025

Qingjuan Li이 [arXiv]에 게시한 ‘Marco-Voice Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Disentanglement

[논문리뷰] Marco-Voice Technical Report

August 8, 2025

Qingjuan Li이 [arXiv]에 게시한 ‘Marco-Voice Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Emotional Speech Dataset

[논문리뷰] Marco-Voice Technical Report

August 8, 2025

Qingjuan Li이 [arXiv]에 게시한 ‘Marco-Voice Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reward Rectification

[논문리뷰] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

August 8, 2025

Xinyu Ye이 [arXiv]에 게시한 ‘On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dynamic Fine-Tuning (DFT)

[논문리뷰] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

August 8, 2025

Xinyu Ye이 [arXiv]에 게시한 ‘On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

PII Redaction

[논문리뷰] PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction

August 8, 2025

Prajit Das이 [arXiv]에 게시한 ‘PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Privacy Preservation

[논문리뷰] PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction

August 8, 2025

Prajit Das이 [arXiv]에 게시한 ‘PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-Domain Generalization

[논문리뷰] PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction

August 8, 2025

Prajit Das이 [arXiv]에 게시한 ‘PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Open-Source LLMs

[논문리뷰] PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction

August 8, 2025

Prajit Das이 [arXiv]에 게시한 ‘PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Evolving LLM

[논문리뷰] R-Zero: Self-Evolving Reasoning LLM from Zero Data

August 8, 2025

Zongxia Li이 [arXiv]에 게시한 ‘R-Zero: Self-Evolving Reasoning LLM from Zero Data’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Zero-Data Training

[논문리뷰] R-Zero: Self-Evolving Reasoning LLM from Zero Data

August 8, 2025

Zongxia Li이 [arXiv]에 게시한 ‘R-Zero: Self-Evolving Reasoning LLM from Zero Data’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Simultaneous Speech Translation

[논문리뷰] REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation

August 8, 2025

Xiao Yu이 [arXiv]에 게시한 ‘REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adaptive Policy

[논문리뷰] REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation

August 8, 2025

Xiao Yu이 [arXiv]에 게시한 ‘REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Entropy-based Loss

[논문리뷰] REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation

August 8, 2025

Xiao Yu이 [arXiv]에 게시한 ‘REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mutual Information

[논문리뷰] REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation

August 8, 2025

Xiao Yu이 [arXiv]에 게시한 ‘REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Latency-Quality Trade-off

[논문리뷰] REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation

August 8, 2025

Xiao Yu이 [arXiv]에 게시한 ‘REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Speech-to-Text Translation

[논문리뷰] REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation

August 8, 2025

Xiao Yu이 [arXiv]에 게시한 ‘REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

REINA

[논문리뷰] REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation

August 8, 2025

Xiao Yu이 [arXiv]에 게시한 ‘REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Robust PCA

[논문리뷰] RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation

August 8, 2025

Jian Yang이 [arXiv]에 게시한 ‘RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Deep Unfolding

[논문리뷰] RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation

August 8, 2025

Jian Yang이 [arXiv]에 게시한 ‘RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sparse Segmentation

[논문리뷰] RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation

August 8, 2025

Jian Yang이 [arXiv]에 게시한 ‘RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image Decomposition

[논문리뷰] RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation

August 8, 2025

Jian Yang이 [arXiv]에 게시한 ‘RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image Compression

[논문리뷰] Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression

August 8, 2025

Yifei Ji이 [arXiv]에 게시한 ‘Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

One-Step Decoding

[논문리뷰] Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression

August 8, 2025

Yifei Ji이 [arXiv]에 게시한 ‘Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fidelity Guidance

[논문리뷰] Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression

August 8, 2025

Yifei Ji이 [arXiv]에 게시한 ‘Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Rate Annealing

[논문리뷰] Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression

August 8, 2025

Yifei Ji이 [arXiv]에 게시한 ‘Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

VAE

[논문리뷰] Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression

August 8, 2025

Yifei Ji이 [arXiv]에 게시한 ‘Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Perceptual Quality

[논문리뷰] Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression

August 8, 2025

Yifei Ji이 [arXiv]에 게시한 ‘Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Strand Generation

[논문리뷰] StrandDesigner: Towards Practical Strand Generation with Sketch Guidance

August 8, 2025

Xiaobin Hu이 [arXiv]에 게시한 ‘StrandDesigner: Towards Practical Strand Generation with Sketch Guidance’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sketch Guidance

[논문리뷰] StrandDesigner: Towards Practical Strand Generation with Sketch Guidance

August 8, 2025

Xiaobin Hu이 [arXiv]에 게시한 ‘StrandDesigner: Towards Practical Strand Generation with Sketch Guidance’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-scale Learning

[논문리뷰] StrandDesigner: Towards Practical Strand Generation with Sketch Guidance

August 8, 2025

Xiaobin Hu이 [arXiv]에 게시한 ‘StrandDesigner: Towards Practical Strand Generation with Sketch Guidance’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adaptive Conditioning

[논문리뷰] StrandDesigner: Towards Practical Strand Generation with Sketch Guidance

August 8, 2025

Xiaobin Hu이 [arXiv]에 게시한 ‘StrandDesigner: Towards Practical Strand Generation with Sketch Guidance’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Hair Modeling

[논문리뷰] StrandDesigner: Towards Practical Strand Generation with Sketch Guidance

August 8, 2025

Xiaobin Hu이 [arXiv]에 게시한 ‘StrandDesigner: Towards Practical Strand Generation with Sketch Guidance’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Document Understanding

[논문리뷰] Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling

August 8, 2025

Ruolin Shen이 [arXiv]에 게시한 ‘Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling’ 논문에 대한 자세한 리뷰입...

Back to Top ↑

Mixed Reward Modeling

[논문리뷰] Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling

August 8, 2025

Ruolin Shen이 [arXiv]에 게시한 ‘Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling’ 논문에 대한 자세한 리뷰입...

Back to Top ↑

Unsupervised Adaptation

[논문리뷰] Adapting Vision-Language Models Without Labels: A Comprehensive Survey

August 11, 2025

Eleni Chatzi이 [arXiv]에 게시한 ‘Adapting Vision-Language Models Without Labels: A Comprehensive Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Test-Time Adaptation (TTA)

[논문리뷰] Adapting Vision-Language Models Without Labels: A Comprehensive Survey

August 11, 2025

Eleni Chatzi이 [arXiv]에 게시한 ‘Adapting Vision-Language Models Without Labels: A Comprehensive Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Domain Transfer

[논문리뷰] Adapting Vision-Language Models Without Labels: A Comprehensive Survey

August 11, 2025

Eleni Chatzi이 [arXiv]에 게시한 ‘Adapting Vision-Language Models Without Labels: A Comprehensive Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gaussian Splatting (GS)

[논문리뷰] GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing

August 11, 2025

Przemysław Spurek이 [arXiv]에 게시한 ‘GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Scene Representation

[논문리뷰] GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing

August 11, 2025

Przemysław Spurek이 [arXiv]에 게시한 ‘GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Physics Simulation

[논문리뷰] GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing

August 11, 2025

Przemysław Spurek이 [arXiv]에 게시한 ‘GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Ray Tracing

[논문리뷰] GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing

August 11, 2025

Przemysław Spurek이 [arXiv]에 게시한 ‘GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Exploration Strategy

[논문리뷰] InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization

August 11, 2025

Pengxiang Li이 [arXiv]에 게시한 ‘InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adaptive Exploration Reward

[논문리뷰] InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization

August 11, 2025

Pengxiang Li이 [arXiv]에 게시한 ‘InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-view Relighting

[논문리뷰] LightSwitch: Multi-view Relighting with Material-guided Diffusion

August 11, 2025

Shubham Tulsiani이 [arXiv]에 게시한 ‘LightSwitch: Multi-view Relighting with Material-guided Diffusion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Material-guided

[논문리뷰] LightSwitch: Multi-view Relighting with Material-guided Diffusion

August 11, 2025

Shubham Tulsiani이 [arXiv]에 게시한 ‘LightSwitch: Multi-view Relighting with Material-guided Diffusion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Inverse Rendering

[논문리뷰] LightSwitch: Multi-view Relighting with Material-guided Diffusion

August 11, 2025

Shubham Tulsiani이 [arXiv]에 게시한 ‘LightSwitch: Multi-view Relighting with Material-guided Diffusion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Consistent Relighting

[논문리뷰] LightSwitch: Multi-view Relighting with Material-guided Diffusion

August 11, 2025

Shubham Tulsiani이 [arXiv]에 게시한 ‘LightSwitch: Multi-view Relighting with Material-guided Diffusion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cultural Groundedness

[논문리뷰] MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs

August 11, 2025

Guohang Yan이 [arXiv]에 게시한 ‘MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Linguistic Capability

[논문리뷰] MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs

August 11, 2025

Guohang Yan이 [arXiv]에 게시한 ‘MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multilingual AI

[논문리뷰] MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs

August 11, 2025

Guohang Yan이 [arXiv]에 게시한 ‘MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Procedural Memory

[논문리뷰] Memp: Exploring Agent Procedural Memory

August 11, 2025

Shuofei Qiao이 [arXiv]에 게시한 ‘Memp: Exploring Agent Procedural Memory’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Task Automation

[논문리뷰] Memp: Exploring Agent Procedural Memory

August 11, 2025

Shuofei Qiao이 [arXiv]에 게시한 ‘Memp: Exploring Agent Procedural Memory’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Experience Replay

[논문리뷰] Memp: Exploring Agent Procedural Memory

August 11, 2025

Shuofei Qiao이 [arXiv]에 게시한 ‘Memp: Exploring Agent Procedural Memory’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agent Learning

[논문리뷰] Memp: Exploring Agent Procedural Memory

August 11, 2025

Shuofei Qiao이 [arXiv]에 게시한 ‘Memp: Exploring Agent Procedural Memory’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mesh Understanding

[논문리뷰] MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh

August 11, 2025

Yi Yang이 [arXiv]에 게시한 ‘MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Primitive-Mesh Decomposition

[논문리뷰] MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh

August 11, 2025

Yi Yang이 [arXiv]에 게시한 ‘MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Surprisal

[논문리뷰] Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal

August 11, 2025

Chengcheng Wan이 [arXiv]에 게시한 ‘Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pruning

[논문리뷰] Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal

August 11, 2025

Chengcheng Wan이 [arXiv]에 게시한 ‘Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Grounding

[논문리뷰] UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding

August 11, 2025

Bingqi Chen이 [arXiv]에 게시한 ‘UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reward Function

[논문리뷰] UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding

August 11, 2025

Bingqi Chen이 [arXiv]에 게시한 ‘UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Resampling

[논문리뷰] UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding

August 11, 2025

Bingqi Chen이 [arXiv]에 게시한 ‘UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Noise Reduction

[논문리뷰] UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding

August 11, 2025

Bingqi Chen이 [arXiv]에 게시한 ‘UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Virtual Try-Off

[논문리뷰] Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off

August 11, 2025

jgkwak이 [arXiv]에 게시한 ‘Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bidirectional Learning

[논문리뷰] Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off

August 11, 2025

jgkwak이 [arXiv]에 게시한 ‘Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fashion Synthesis

[논문리뷰] Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off

August 11, 2025

jgkwak이 [arXiv]에 게시한 ‘Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Evolving AI Agents

[논문리뷰] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

August 12, 2025

Xinhao Yi이 [arXiv]에 게시한 ‘A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems’ 논문에 대한 자세...

Back to Top ↑

Agent Optimization

[논문리뷰] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

August 12, 2025

Xinhao Yi이 [arXiv]에 게시한 ‘A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems’ 논문에 대한 자세...

Back to Top ↑

CLIP Latent

[논문리뷰] Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents

August 12, 2025

Mohit Bansal이 [arXiv]에 게시한 ‘Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

ControlNet

[논문리뷰] Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents

August 12, 2025

Mohit Bansal이 [arXiv]에 게시한 ‘Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Deep-Research Agents

[논문리뷰] BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

August 12, 2025

Kai Zou이 [arXiv]에 게시한 ‘BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Retrieval

[논문리뷰] BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

August 12, 2025

Kai Zou이 [arXiv]에 게시한 ‘BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Curated Corpus

[논문리뷰] BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

August 12, 2025

Kai Zou이 [arXiv]에 게시한 ‘BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Transparency

[논문리뷰] BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

August 12, 2025

Kai Zou이 [arXiv]에 게시한 ‘BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Step Entropy

[논문리뷰] Compressing Chain-of-Thought in LLMs via Step Entropy

August 12, 2025

Zhijian Xu이 [arXiv]에 게시한 ‘Compressing Chain-of-Thought in LLMs via Step Entropy’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

SFT

[논문리뷰] Compressing Chain-of-Thought in LLMs via Step Entropy

August 12, 2025

Zhijian Xu이 [arXiv]에 게시한 ‘Compressing Chain-of-Thought in LLMs via Step Entropy’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

사전 학습

[논문리뷰] Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs

August 12, 2025

Robert Kirk이 [arXiv]에 게시한 ‘Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

변조 저항성

[논문리뷰] Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs

August 12, 2025

Robert Kirk이 [arXiv]에 게시한 ‘Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

바이오위협

[논문리뷰] Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs

August 12, 2025

Robert Kirk이 [arXiv]에 게시한 ‘Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AI 안전

[논문리뷰] Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs

August 12, 2025

Robert Kirk이 [arXiv]에 게시한 ‘Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

서킷 브레이킹

[논문리뷰] Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs

August 12, 2025

Robert Kirk이 [arXiv]에 게시한 ‘Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

머신 언러닝

[논문리뷰] Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs

August 12, 2025

Robert Kirk이 [arXiv]에 게시한 ‘Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Poisoning Attack

[논문리뷰] Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System

August 12, 2025

Reynold Cheng이 [arXiv]에 게시한 ‘Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fact-checking

[논문리뷰] Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System

August 12, 2025

Reynold Cheng이 [arXiv]에 게시한 ‘Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

System Security

[논문리뷰] Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System

August 12, 2025

Reynold Cheng이 [arXiv]에 게시한 ‘Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Shape Transformation

[논문리뷰] Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control

August 12, 2025

Hongyu Liu이 [arXiv]에 게시한 ‘Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Trajectory Divergence Map

[논문리뷰] Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control

August 12, 2025

Hongyu Liu이 [arXiv]에 게시한 ‘Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Region Control

[논문리뷰] Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control

August 12, 2025

Hongyu Liu이 [arXiv]에 게시한 ‘Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sequence Classification

[논문리뷰] GLiClass: Generalist Lightweight Model for Sequence Classification Tasks

August 12, 2025

Alexander Yavorskyi이 [arXiv]에 게시한 ‘GLiClass: Generalist Lightweight Model for Sequence Classification Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-label Classification

[논문리뷰] GLiClass: Generalist Lightweight Model for Sequence Classification Tasks

August 12, 2025

Alexander Yavorskyi이 [arXiv]에 게시한 ‘GLiClass: Generalist Lightweight Model for Sequence Classification Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GLiNER

[논문리뷰] GLiClass: Generalist Lightweight Model for Sequence Classification Tasks

August 12, 2025

Alexander Yavorskyi이 [arXiv]에 게시한 ‘GLiClass: Generalist Lightweight Model for Sequence Classification Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

MoE Architecture

[논문리뷰] Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts

August 12, 2025

Tieyuan Chen이 [arXiv]에 게시한 ‘Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dynamic Activation

[논문리뷰] Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts

August 12, 2025

Tieyuan Chen이 [arXiv]에 게시한 ‘Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adjugate Experts

[논문리뷰] Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts

August 12, 2025

Tieyuan Chen이 [arXiv]에 게시한 ‘Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Upcycling Strategy

[논문리뷰] Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts

August 12, 2025

Tieyuan Chen이 [arXiv]에 게시한 ‘Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Load Balancing

[논문리뷰] Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts

August 12, 2025

Tieyuan Chen이 [arXiv]에 게시한 ‘Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning LLMs

[논문리뷰] Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization

August 12, 2025

Guanting Dong이 [arXiv]에 게시한 ‘Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gradient Clipping

[논문리뷰] Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization

August 12, 2025

Guanting Dong이 [arXiv]에 게시한 ‘Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Global Locality

[논문리뷰] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning

August 12, 2025

Baihong Yuan이 [arXiv]에 게시한 ‘Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Matrix Decomposition

[논문리뷰] MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs

August 12, 2025

Jianguo Li이 [arXiv]에 게시한 ‘MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Action Reasoning

[논문리뷰] MolmoAct: Action Reasoning Models that can Reason in Space

August 12, 2025

Shuo Liu이 [arXiv]에 게시한 ‘MolmoAct: Action Reasoning Models that can Reason in Space’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spatial Planning

[논문리뷰] MolmoAct: Action Reasoning Models that can Reason in Space

August 12, 2025

Shuo Liu이 [arXiv]에 게시한 ‘MolmoAct: Action Reasoning Models that can Reason in Space’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Depth Perception

[논문리뷰] MolmoAct: Action Reasoning Models that can Reason in Space

August 12, 2025

Shuo Liu이 [arXiv]에 게시한 ‘MolmoAct: Action Reasoning Models that can Reason in Space’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Trajectory Generation

[논문리뷰] MolmoAct: Action Reasoning Models that can Reason in Space

August 12, 2025

Shuo Liu이 [arXiv]에 게시한 ‘MolmoAct: Action Reasoning Models that can Reason in Space’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Effects

[논문리뷰] Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation

August 12, 2025

Xiaokun Feng이 [arXiv]에 게시한 ‘Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spatial Control

[논문리뷰] Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation

August 12, 2025

Xiaokun Feng이 [arXiv]에 게시한 ‘Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-VFX

[논문리뷰] Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation

August 12, 2025

Xiaokun Feng이 [arXiv]에 게시한 ‘Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agent Reasoning

[논문리뷰] OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks

August 12, 2025

Hongxing Li이 [arXiv]에 게시한 ‘OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Physical Interaction

[논문리뷰] OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks

August 12, 2025

Hongxing Li이 [arXiv]에 게시한 ‘OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Constraint Reasoning

[논문리뷰] OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks

August 12, 2025

Hongxing Li이 [arXiv]에 게시한 ‘OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Clipping

[논문리뷰] Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning

August 12, 2025

Jiaheng Liu이 [arXiv]에 게시한 ‘Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Overlong Filtering

[논문리뷰] Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning

August 12, 2025

Jiaheng Liu이 [arXiv]에 게시한 ‘Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Passage Ranking

[논문리뷰] ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability

August 12, 2025

Yuchen Li이 [arXiv]에 게시한 ‘ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Listwise Reranking

[논문리뷰] ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability

August 12, 2025

Yuchen Li이 [arXiv]에 게시한 ‘ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Computer Vision (CV)

[논문리뷰] Reinforcement Learning in Vision: A Survey

August 12, 2025

Qingwei Meng이 [arXiv]에 게시한 ‘Reinforcement Learning in Vision: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Shortcut Learning

[논문리뷰] Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation

August 12, 2025

Hengtao Shen이 [arXiv]에 게시한 ‘Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dataset Diversity

[논문리뷰] Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation

August 12, 2025

Hengtao Shen이 [arXiv]에 게시한 ‘Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dataset Fragmentation

[논문리뷰] Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation

August 12, 2025

Hengtao Shen이 [arXiv]에 게시한 ‘Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Speech-to-LaTeX

[논문리뷰] Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences

August 12, 2025

Matvey Skripkin이 [arXiv]에 게시한 ‘Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mathematical Expression Recognition

[논문리뷰] Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences

August 12, 2025

Matvey Skripkin이 [arXiv]에 게시한 ‘Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LaTeX Generation

[논문리뷰] Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences

August 12, 2025

Matvey Skripkin이 [arXiv]에 게시한 ‘Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Rewarding LLMs

[논문리뷰] Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future

August 12, 2025

Qiufeng Wang이 [arXiv]에 게시한 ‘Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gradient Collapse

[논문리뷰] Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future

August 12, 2025

Qiufeng Wang이 [arXiv]에 게시한 ‘Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Iterative Optimization

[논문리뷰] Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future

August 12, 2025

Qiufeng Wang이 [arXiv]에 게시한 ‘Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

User-Centric AI

[논문리뷰] UserBench: An Interactive Gym Environment for User-Centric Agents

August 12, 2025

Jianguo Zhang이 [arXiv]에 게시한 ‘UserBench: An Interactive Gym Environment for User-Centric Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Interactive Agents

[논문리뷰] UserBench: An Interactive Gym Environment for User-Centric Agents

August 12, 2025

Jianguo Zhang이 [arXiv]에 게시한 ‘UserBench: An Interactive Gym Environment for User-Centric Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gym Environment

[논문리뷰] UserBench: An Interactive Gym Environment for User-Centric Agents

August 12, 2025

Jianguo Zhang이 [arXiv]에 게시한 ‘UserBench: An Interactive Gym Environment for User-Centric Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Preference Elicitation

[논문리뷰] UserBench: An Interactive Gym Environment for User-Centric Agents

August 12, 2025

Jianguo Zhang이 [arXiv]에 게시한 ‘UserBench: An Interactive Gym Environment for User-Centric Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long Document Understanding

[논문리뷰] VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

August 12, 2025

Tong Yu이 [arXiv]에 게시한 ‘VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual QA

[논문리뷰] VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

August 12, 2025

Tong Yu이 [arXiv]에 게시한 ‘VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Table Understanding

[논문리뷰] VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

August 12, 2025

Tong Yu이 [arXiv]에 게시한 ‘VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Jailbreak Attack

[논문리뷰] When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs

August 12, 2025

Dasol Choi이 [arXiv]에 게시한 ‘When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adversarial Audio

[논문리뷰] When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs

August 12, 2025

Dasol Choi이 [arXiv]에 게시한 ‘When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Projected Gradient Descent

[논문리뷰] When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs

August 12, 2025

Dasol Choi이 [arXiv]에 게시한 ‘When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Native Payload Discovery

[논문리뷰] When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs

August 12, 2025

Dasol Choi이 [arXiv]에 게시한 ‘When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal AI Safety

[논문리뷰] When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs

August 12, 2025

Dasol Choi이 [arXiv]에 게시한 ‘When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Structured Output

[논문리뷰] WideSearch: Benchmarking Agentic Broad Info-Seeking

August 12, 2025

Yan Gao이 [arXiv]에 게시한 ‘WideSearch: Benchmarking Agentic Broad Info-Seeking’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Promotion

[논문리뷰] Adversarial Video Promotion Against Text-to-Video Retrieval

August 13, 2025

Shuai Liu이 [arXiv]에 게시한 ‘Adversarial Video Promotion Against Text-to-Video Retrieval’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-to-Video Retrieval

[논문리뷰] Adversarial Video Promotion Against Text-to-Video Retrieval

August 13, 2025

Shuai Liu이 [arXiv]에 게시한 ‘Adversarial Video Promotion Against Text-to-Video Retrieval’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Modality Refinement

[논문리뷰] Adversarial Video Promotion Against Text-to-Video Retrieval

August 13, 2025

Shuai Liu이 [arXiv]에 게시한 ‘Adversarial Video Promotion Against Text-to-Video Retrieval’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Black-box Attack

[논문리뷰] Adversarial Video Promotion Against Text-to-Video Retrieval

August 13, 2025

Shuai Liu이 [arXiv]에 게시한 ‘Adversarial Video Promotion Against Text-to-Video Retrieval’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Manipulation

[논문리뷰] Adversarial Video Promotion Against Text-to-Video Retrieval

August 13, 2025

Shuai Liu이 [arXiv]에 게시한 ‘Adversarial Video Promotion Against Text-to-Video Retrieval’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Transferability

[논문리뷰] Adversarial Video Promotion Against Text-to-Video Retrieval

August 13, 2025

Shuai Liu이 [arXiv]에 게시한 ‘Adversarial Video Promotion Against Text-to-Video Retrieval’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Language Model

[논문리뷰] Aryabhata: An exam-focused language model for JEE Math

August 13, 2025

Sandeep Varma이 [arXiv]에 게시한 ‘Aryabhata: An exam-focused language model for JEE Math’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

JEE

[논문리뷰] Aryabhata: An exam-focused language model for JEE Math

August 13, 2025

Sandeep Varma이 [arXiv]에 게시한 ‘Aryabhata: An exam-focused language model for JEE Math’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

코드 생성

[논문리뷰] AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators

August 13, 2025

Tao Zhang이 [arXiv]에 게시한 ‘AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

코드 벤치마크

[논문리뷰] AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators

August 13, 2025

Tao Zhang이 [arXiv]에 게시한 ‘AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

다국어 프로그래밍

[논문리뷰] AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators

August 13, 2025

Tao Zhang이 [arXiv]에 게시한 ‘AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

자동화된 데이터 생성

[논문리뷰] AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators

August 13, 2025

Tao Zhang이 [arXiv]에 게시한 ‘AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

샌드박스 평가

[논문리뷰] AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators

August 13, 2025

Tao Zhang이 [arXiv]에 게시한 ‘AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Asynchronous RL

[논문리뷰] Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL

August 13, 2025

Chuyi He이 [arXiv]에 게시한 ‘Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Attention Steering

[논문리뷰] BiasGym: Fantastic Biases and How to Find (and Remove) Them

August 13, 2025

Arnav Arora이 [arXiv]에 게시한 ‘BiasGym: Fantastic Biases and How to Find (and Remove) Them’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Stereotype Analysis

[논문리뷰] BiasGym: Fantastic Biases and How to Find (and Remove) Them

August 13, 2025

Arnav Arora이 [arXiv]에 게시한 ‘BiasGym: Fantastic Biases and How to Find (and Remove) Them’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Quantum Game Theory

[논문리뷰] Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mitigation on NISQ Hardware

August 13, 2025

Jhon Alejandro Andrade이 [arXiv]에 게시한 ‘Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mit...

Back to Top ↑

NISQ Hardware

[논문리뷰] Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mitigation on NISQ Hardware

August 13, 2025

Jhon Alejandro Andrade이 [arXiv]에 게시한 ‘Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mit...

Back to Top ↑

Error Mitigation

[논문리뷰] Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mitigation on NISQ Hardware

August 13, 2025

Jhon Alejandro Andrade이 [arXiv]에 게시한 ‘Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mit...

Back to Top ↑

Battle of the Sexes

[논문리뷰] Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mitigation on NISQ Hardware

August 13, 2025

Jhon Alejandro Andrade이 [arXiv]에 게시한 ‘Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mit...

Back to Top ↑

Qiskit

[논문리뷰] Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mitigation on NISQ Hardware

August 13, 2025

Jhon Alejandro Andrade이 [arXiv]에 게시한 ‘Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mit...

Back to Top ↑

Quantum Computing

[논문리뷰] Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mitigation on NISQ Hardware

August 13, 2025

Jhon Alejandro Andrade이 [arXiv]에 게시한 ‘Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mit...

Back to Top ↑

Strategic Coordination

[논문리뷰] Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mitigation on NISQ Hardware

August 13, 2025

Jhon Alejandro Andrade이 [arXiv]에 게시한 ‘Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mit...

Back to Top ↑

Payoff Maximization

[논문리뷰] Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mitigation on NISQ Hardware

August 13, 2025

Jhon Alejandro Andrade이 [arXiv]에 게시한 ‘Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mit...

Back to Top ↑

4D Character Animation

[논문리뷰] CharacterShot: Controllable and Consistent 4D Character Animation

August 13, 2025

Fei Shen이 [arXiv]에 게시한 ‘CharacterShot: Controllable and Consistent 4D Character Animation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Character Dataset

[논문리뷰] CharacterShot: Controllable and Consistent 4D Character Animation

August 13, 2025

Fei Shen이 [arXiv]에 게시한 ‘CharacterShot: Controllable and Consistent 4D Character Animation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Next Shot Generation

[논문리뷰] Cut2Next: Generating Next Shot via In-Context Tuning

August 13, 2025

Yu Qiao이 [arXiv]에 게시한 ‘Cut2Next: Generating Next Shot via In-Context Tuning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

In-Context Tuning

[논문리뷰] Cut2Next: Generating Next Shot via In-Context Tuning

August 13, 2025

Yu Qiao이 [arXiv]에 게시한 ‘Cut2Next: Generating Next Shot via In-Context Tuning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cinematic Continuity

[논문리뷰] Cut2Next: Generating Next Shot via In-Context Tuning

August 13, 2025

Yu Qiao이 [arXiv]에 게시한 ‘Cut2Next: Generating Next Shot via In-Context Tuning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hierarchical Prompting

[논문리뷰] Cut2Next: Generating Next Shot via In-Context Tuning

August 13, 2025

Yu Qiao이 [arXiv]에 게시한 ‘Cut2Next: Generating Next Shot via In-Context Tuning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Shot Editing

[논문리뷰] Cut2Next: Generating Next Shot via In-Context Tuning

August 13, 2025

Yu Qiao이 [arXiv]에 게시한 ‘Cut2Next: Generating Next Shot via In-Context Tuning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Decoder-Centric

[논문리뷰] DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition

August 13, 2025

Lukáš Burget이 [arXiv]에 게시한 ‘DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Intermediate Supervision

[논문리뷰] DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition

August 13, 2025

Lukáš Burget이 [arXiv]에 게시한 ‘DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Out-of-Domain Generalization

[논문리뷰] DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition

August 13, 2025

Lukáš Burget이 [arXiv]에 게시한 ‘DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Internal Language Model

[논문리뷰] DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition

August 13, 2025

Lukáš Burget이 [arXiv]에 게시한 ‘DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Diplomacy Game

[논문리뷰] Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy

August 13, 2025

Elizabeth Karpinski이 [arXiv]에 게시한 ‘Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Strategic Reasoning

[논문리뷰] Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy

August 13, 2025

Elizabeth Karpinski이 [arXiv]에 게시한 ‘Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Behavioral Analysis

[논문리뷰] Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy

August 13, 2025

Elizabeth Karpinski이 [arXiv]에 게시한 ‘Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Automated Environment Generation

[논문리뷰] Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments

August 13, 2025

Xuesong Yao이 [arXiv]에 게시한 ‘Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Feedback-Driven Training

[논문리뷰] Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments

August 13, 2025

Xuesong Yao이 [arXiv]에 게시한 ‘Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reward Mechanism

[논문리뷰] Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments

August 13, 2025

Xuesong Yao이 [arXiv]에 게시한 ‘Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Contextual Understanding

[논문리뷰] Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments

August 13, 2025

Xuesong Yao이 [arXiv]에 게시한 ‘Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Replay

[논문리뷰] GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay

August 13, 2025

Yang Fan이 [arXiv]에 게시한 ‘GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Activation States

[논문리뷰] GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay

August 13, 2025

Yang Fan이 [arXiv]에 게시한 ‘GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Anti-forgetting

[논문리뷰] GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay

August 13, 2025

Yang Fan이 [arXiv]에 게시한 ‘GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Threshold-based Margin Loss

[논문리뷰] GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay

August 13, 2025

Yang Fan이 [arXiv]에 게시한 ‘GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hierarchical Reinforcement Learning

[논문리뷰] HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches

August 13, 2025

Qiang Ju이 [arXiv]에 게시한 ‘HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-source RAG

[논문리뷰] HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches

August 13, 2025

Qiang Ju이 [arXiv]에 게시한 ‘HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Knowledge Integration

[논문리뷰] HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches

August 13, 2025

Qiang Ju이 [arXiv]에 게시한 ‘HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Enterprise Search

[논문리뷰] HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches

August 13, 2025

Qiang Ju이 [arXiv]에 게시한 ‘HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Panoramic Video Generation

[논문리뷰] Matrix-3D: Omnidirectional Explorable 3D World Generation

August 13, 2025

Yuqi Li이 [arXiv]에 게시한 ‘Matrix-3D: Omnidirectional Explorable 3D World Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Camera Control

[논문리뷰] Matrix-3D: Omnidirectional Explorable 3D World Generation

August 13, 2025

Yuqi Li이 [arXiv]에 게시한 ‘Matrix-3D: Omnidirectional Explorable 3D World Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Paralinguistic Vocalizations

[논문리뷰] NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations

August 13, 2025

Haoyue Zhan이 [arXiv]에 게시한 ‘NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Annotation

[논문리뷰] NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations

August 13, 2025

Haoyue Zhan이 [arXiv]에 게시한 ‘NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mandarin Speech

[논문리뷰] NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations

August 13, 2025

Haoyue Zhan이 [arXiv]에 게시한 ‘NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Expressive Speech

[논문리뷰] NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations

August 13, 2025

Haoyue Zhan이 [arXiv]에 게시한 ‘NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Computer-Use Agents

[논문리뷰] OpenCUA: Open Foundations for Computer-Use Agents

August 13, 2025

Tianbao Xie이 [arXiv]에 게시한 ‘OpenCUA: Open Foundations for Computer-Use Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Chain-of-Thought Reasoning

[논문리뷰] OpenCUA: Open Foundations for Computer-Use Agents

August 13, 2025

Tianbao Xie이 [arXiv]에 게시한 ‘OpenCUA: Open Foundations for Computer-Use Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Open-source Framework

[논문리뷰] OpenCUA: Open Foundations for Computer-Use Agents

August 13, 2025

Tianbao Xie이 [arXiv]에 게시한 ‘OpenCUA: Open Foundations for Computer-Use Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Desktop Automation

[논문리뷰] OpenCUA: Open Foundations for Computer-Use Agents

August 13, 2025

Tianbao Xie이 [arXiv]에 게시한 ‘OpenCUA: Open Foundations for Computer-Use Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Region Consistency

[논문리뷰] Test-Time Reinforcement Learning for GUI Grounding via Region Consistency

August 13, 2025

Zhengxi Lu이 [arXiv]에 게시한 ‘Test-Time Reinforcement Learning for GUI Grounding via Region Consistency’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spatial Voting

[논문리뷰] Test-Time Reinforcement Learning for GUI Grounding via Region Consistency

August 13, 2025

Zhengxi Lu이 [arXiv]에 게시한 ‘Test-Time Reinforcement Learning for GUI Grounding via Region Consistency’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Temporal Oscillation

[논문리뷰] Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models

August 13, 2025

Chenchen Jing이 [arXiv]에 게시한 ‘Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Consistency Voting

[논문리뷰] Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models

August 13, 2025

Chenchen Jing이 [arXiv]에 게시한 ‘Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Temporal Semantic Entropy

[논문리뷰] Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models

August 13, 2025

Chenchen Jing이 [arXiv]에 게시한 ‘Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Low-Resource MT

[논문리뷰] TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation

August 13, 2025

Rachel Bawden이 [arXiv]에 게시한 ‘TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Back-Translation

[논문리뷰] TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation

August 13, 2025

Rachel Bawden이 [arXiv]에 게시한 ‘TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

In-Context Learning (ICL)

[논문리뷰] TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation

August 13, 2025

Rachel Bawden이 [arXiv]에 게시한 ‘TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Topic-Guided Generation

[논문리뷰] TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation

August 13, 2025

Rachel Bawden이 [arXiv]에 게시한 ‘TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Parallel Data Synthesis

[논문리뷰] TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation

August 13, 2025

Rachel Bawden이 [arXiv]에 게시한 ‘TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Robotic Dexterous Grasping

[논문리뷰] Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors

August 13, 2025

Haoran Xu이 [arXiv]에 게시한 ‘Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Affordance-Aware

[논문리뷰] Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors

August 13, 2025

Haoran Xu이 [arXiv]에 게시한 ‘Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human-like Priors

[논문리뷰] Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors

August 13, 2025

Haoran Xu이 [arXiv]에 게시한 ‘Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Two-Stage Training

[논문리뷰] Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors

August 13, 2025

Haoran Xu이 [arXiv]에 게시한 ‘Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Manipulation

[논문리뷰] Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors

August 13, 2025

Haoran Xu이 [arXiv]에 게시한 ‘Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning Efficiency

[논문리뷰] Train Long, Think Short: Curriculum Learning for Efficient Reasoning

August 13, 2025

Marzyeh Ghassemi이 [arXiv]에 게시한 ‘Train Long, Think Short: Curriculum Learning for Efficient Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Token Budget Control

[논문리뷰] Train Long, Think Short: Curriculum Learning for Efficient Reasoning

August 13, 2025

Marzyeh Ghassemi이 [arXiv]에 게시한 ‘Train Long, Think Short: Curriculum Learning for Efficient Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Group Relative Policy Optimization

[논문리뷰] Train Long, Think Short: Curriculum Learning for Efficient Reasoning

August 13, 2025

Marzyeh Ghassemi이 [arXiv]에 게시한 ‘Train Long, Think Short: Curriculum Learning for Efficient Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Masked Generative Transformers

[논문리뷰] UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation

August 13, 2025

Kevin Galim이 [arXiv]에 게시한 ‘UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Compositional Generation

[논문리뷰] UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation

August 13, 2025

Kevin Galim이 [arXiv]에 게시한 ‘UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Attention Guidance

[논문리뷰] UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation

August 13, 2025

Kevin Galim이 [arXiv]에 게시한 ‘UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Unmasking Strategy

[논문리뷰] UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation

August 13, 2025

Kevin Galim이 [arXiv]에 게시한 ‘UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Attribute Binding

[논문리뷰] UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation

August 13, 2025

Kevin Galim이 [arXiv]에 게시한 ‘UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mesh Generation

[논문리뷰] VertexRegen: Mesh Generation with Continuous Level of Detail

August 13, 2025

Jakob Engel이 [arXiv]에 게시한 ‘VertexRegen: Mesh Generation with Continuous Level of Detail’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Level of Detail (LOD)

[논문리뷰] VertexRegen: Mesh Generation with Continuous Level of Detail

August 13, 2025

Jakob Engel이 [arXiv]에 게시한 ‘VertexRegen: Mesh Generation with Continuous Level of Detail’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Progressive Meshes

[논문리뷰] VertexRegen: Mesh Generation with Continuous Level of Detail

August 13, 2025

Jakob Engel이 [arXiv]에 게시한 ‘VertexRegen: Mesh Generation with Continuous Level of Detail’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vertex Split

[논문리뷰] VertexRegen: Mesh Generation with Continuous Level of Detail

August 13, 2025

Jakob Engel이 [arXiv]에 게시한 ‘VertexRegen: Mesh Generation with Continuous Level of Detail’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Graphics

[논문리뷰] VertexRegen: Mesh Generation with Continuous Level of Detail

August 13, 2025

Jakob Engel이 [arXiv]에 게시한 ‘VertexRegen: Mesh Generation with Continuous Level of Detail’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spatio-Temporal Fusion

[논문리뷰] WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion

August 13, 2025

Rachid Nedjai이 [arXiv]에 게시한 ‘WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion’ 논문에 대...

Back to Top ↑

Land Surface Temperature

[논문리뷰] WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion

August 13, 2025

Rachid Nedjai이 [arXiv]에 게시한 ‘WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion’ 논문에 대...

Back to Top ↑

Generative Adversarial Network

[논문리뷰] WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion

August 13, 2025

Rachid Nedjai이 [arXiv]에 게시한 ‘WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion’ 논문에 대...

Back to Top ↑

Weakly-Supervised Learning

[논문리뷰] WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion

August 13, 2025

Rachid Nedjai이 [arXiv]에 게시한 ‘WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion’ 논문에 대...

Back to Top ↑

Meta-learning

[논문리뷰] AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance

August 14, 2025

Yong Li이 [arXiv]에 게시한 ‘AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adaptive Control

[논문리뷰] AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance

August 14, 2025

Yong Li이 [arXiv]에 게시한 ‘AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agent Stability

[논문리뷰] AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving

August 14, 2025

Jinjie Gu이 [arXiv]에 게시한 ‘AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dynamic Supervision

[논문리뷰] AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving

August 14, 2025

Jinjie Gu이 [arXiv]에 게시한 ‘AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Maneuvering

[논문리뷰] AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving

August 14, 2025

Jinjie Gu이 [arXiv]에 게시한 ‘AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Explainable NLP

[논문리뷰] Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study

August 14, 2025

Gjergji Kasneci이 [arXiv]에 게시한 ‘Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Natural Language Explanations

[논문리뷰] Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study

August 14, 2025

Gjergji Kasneci이 [arXiv]에 게시한 ‘Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pre-trained Language Models

[논문리뷰] Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study

August 14, 2025

Gjergji Kasneci이 [arXiv]에 게시한 ‘Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Natural Language Inference

[논문리뷰] Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study

August 14, 2025

Gjergji Kasneci이 [arXiv]에 게시한 ‘Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Performance Enhancement

[논문리뷰] Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study

August 14, 2025

Gjergji Kasneci이 [arXiv]에 게시한 ‘Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hybrid Annotation

[논문리뷰] Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models

August 14, 2025

Guiyang Hou이 [arXiv]에 게시한 ‘Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Faster Inference

[논문리뷰] Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing

August 14, 2025

Hao Zhang이 [arXiv]에 게시한 ‘Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Discrete Diffusion Forcing (D2F)

[논문리뷰] Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing

August 14, 2025

Hao Zhang이 [arXiv]에 게시한 ‘Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GPT-4o

[논문리뷰] Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation

August 14, 2025

Zhenghao Hu이 [arXiv]에 게시한 ‘Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Surreal Image Generation

[논문리뷰] Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation

August 14, 2025

Zhenghao Hu이 [arXiv]에 게시한 ‘Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Artifact Restoration

[논문리뷰] GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors

August 14, 2025

Qingnan Fan이 [arXiv]에 게시한 ‘GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sparse-view 3D Reconstruction

[논문리뷰] GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors

August 14, 2025

Qingnan Fan이 [arXiv]에 게시한 ‘GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reference-Guided

[논문리뷰] GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors

August 14, 2025

Qingnan Fan이 [arXiv]에 게시한 ‘GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Backdoor Attack

[논문리뷰] IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding

August 14, 2025

Di Zhang이 [arXiv]에 게시한 ‘IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Input-aware Trigger

[논문리뷰] IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding

August 14, 2025

Di Zhang이 [arXiv]에 게시한 ‘IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Security

[논문리뷰] IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding

August 14, 2025

Di Zhang이 [arXiv]에 게시한 ‘IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Open-vocabulary

[논문리뷰] IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding

August 14, 2025

Di Zhang이 [arXiv]에 게시한 ‘IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Group Relative Alignment Optimization

[논문리뷰] Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment

August 14, 2025

Lei Fan이 [arXiv]에 게시한 ‘Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Optimization

[논문리뷰] Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment

August 14, 2025

Lei Fan이 [arXiv]에 게시한 ‘Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-World Benchmark

[논문리뷰] MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models

August 14, 2025

Zhihan Zhou이 [arXiv]에 게시한 ‘MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models’ 논문에 대한 자세한 리뷰...

Back to Top ↑

K-12 Education

[논문리뷰] MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models

August 14, 2025

Zhihan Zhou이 [arXiv]에 게시한 ‘MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models’ 논문에 대한 자세한 리뷰...

Back to Top ↑

Molecule Discovery

[논문리뷰] Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery

August 14, 2025

Di Zhang이 [arXiv]에 게시한 ‘Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Molecular Generation

[논문리뷰] Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery

August 14, 2025

Di Zhang이 [arXiv]에 게시한 ‘Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hypernetworks

[논문리뷰] Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models

August 14, 2025

Zeynep Akata이 [arXiv]에 게시한 ‘Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reward-Guided Generation

[논문리뷰] Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models

August 14, 2025

Zeynep Akata이 [arXiv]에 게시한 ‘Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Latent Space Optimization

[논문리뷰] Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models

August 14, 2025

Zeynep Akata이 [arXiv]에 게시한 ‘Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Agent

[논문리뷰] Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory

August 14, 2025

Yuan Lin이 [arXiv]에 게시한 ‘Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long-Term Memory

[논문리뷰] Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory

August 14, 2025

Yuan Lin이 [arXiv]에 게시한 ‘Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Episodic Memory

[논문리뷰] Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory

August 14, 2025

Yuan Lin이 [arXiv]에 게시한 ‘Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semantic Memory

[논문리뷰] Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory

August 14, 2025

Yuan Lin이 [arXiv]에 게시한 ‘Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Entity-Centric Memory

[논문리뷰] Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory

August 14, 2025

Yuan Lin이 [arXiv]에 게시한 ‘Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Plug-and-Play

[논문리뷰] Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation

August 14, 2025

Chen Li이 [arXiv]에 게시한 ‘Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Attention

[논문리뷰] Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation

August 14, 2025

Chen Li이 [arXiv]에 게시한 ‘Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Lightweight AI

[논문리뷰] Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation

August 14, 2025

Chen Li이 [arXiv]에 게시한 ‘Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Conditional Image Branch

[논문리뷰] Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation

August 14, 2025

Chen Li이 [arXiv]에 게시한 ‘Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Storyboard Generation

[논문리뷰] Story2Board: A Training-Free Approach for Expressive Storyboard Generation

August 14, 2025

Dani Lischinski이 [arXiv]에 게시한 ‘Story2Board: A Training-Free Approach for Expressive Storyboard Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Character Consistency

[논문리뷰] Story2Board: A Training-Free Approach for Expressive Storyboard Generation

August 14, 2025

Dani Lischinski이 [arXiv]에 게시한 ‘Story2Board: A Training-Free Approach for Expressive Storyboard Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scene Diversity

[논문리뷰] Story2Board: A Training-Free Approach for Expressive Storyboard Generation

August 14, 2025

Dani Lischinski이 [arXiv]에 게시한 ‘Story2Board: A Training-Free Approach for Expressive Storyboard Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Storytelling

[논문리뷰] Story2Board: A Training-Free Approach for Expressive Storyboard Generation

August 14, 2025

Dani Lischinski이 [arXiv]에 게시한 ‘Story2Board: A Training-Free Approach for Expressive Storyboard Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Task Vectors

[논문리뷰] VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models

August 14, 2025

Dongdong Zhang이 [arXiv]에 게시한 ‘VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Coding LLM

[논문리뷰] VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models

August 14, 2025

Dongdong Zhang이 [arXiv]에 게시한 ‘VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Automated Interpreting Assessment

[논문리뷰] From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms

August 15, 2025

Ziyin Zhang이 [arXiv]에 게시한 ‘From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms’ 논문에 대한 자세한 ...

Back to Top ↑

SHAP

[논문리뷰] From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms

August 15, 2025

Ziyin Zhang이 [arXiv]에 게시한 ‘From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms’ 논문에 대한 자세한 ...

Back to Top ↑

Interpreting Quality

[논문리뷰] From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms

August 15, 2025

Ziyin Zhang이 [arXiv]에 게시한 ‘From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms’ 논문에 대한 자세한 ...

Back to Top ↑

Human-Centered AI

[논문리뷰] HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs

August 15, 2025

Yi Yuan이 [arXiv]에 게시한 ‘HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Empathy

[논문리뷰] HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs

August 15, 2025

Yi Yuan이 [arXiv]에 게시한 ‘HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

MLLM Benchmark

[논문리뷰] HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs

August 15, 2025

Yi Yuan이 [arXiv]에 게시한 ‘HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Continuous Latent Tokens

[논문리뷰] NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

August 15, 2025

Quan Sun이 [arXiv]에 게시한 ‘NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long-Context Understanding

[논문리뷰] PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts

August 15, 2025

Rui Lu이 [arXiv]에 게시한 ‘PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLMs Evaluation

[논문리뷰] PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts

August 15, 2025

Rui Lu이 [arXiv]에 게시한 ‘PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Global Comprehension

[논문리뷰] PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts

August 15, 2025

Rui Lu이 [arXiv]에 게시한 ‘PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fluid Intelligence

[논문리뷰] PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts

August 15, 2025

Rui Lu이 [arXiv]에 게시한 ‘PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Prequel Entailment

[논문리뷰] PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts

August 15, 2025

Rui Lu이 [arXiv]에 게시한 ‘PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Encoders

[논문리뷰] Processing and acquisition traces in visual encoders: What does CLIP know about your camera?

August 15, 2025

Giorgos Tolias이 [arXiv]에 게시한 ‘Processing and acquisition traces in visual encoders: What does CLIP know about your camera?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Metadata

[논문리뷰] Processing and acquisition traces in visual encoders: What does CLIP know about your camera?

August 15, 2025

Giorgos Tolias이 [arXiv]에 게시한 ‘Processing and acquisition traces in visual encoders: What does CLIP know about your camera?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image Acquisition

[논문리뷰] Processing and acquisition traces in visual encoders: What does CLIP know about your camera?

August 15, 2025

Giorgos Tolias이 [arXiv]에 게시한 ‘Processing and acquisition traces in visual encoders: What does CLIP know about your camera?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Causal Transformer

[논문리뷰] STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer

August 15, 2025

Honghua Chen이 [arXiv]에 게시한 ‘STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sequential Modeling

[논문리뷰] STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer

August 15, 2025

Honghua Chen이 [arXiv]에 게시한 ‘STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Streaming Data

[논문리뷰] STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer

August 15, 2025

Honghua Chen이 [arXiv]에 게시한 ‘STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pointmap Prediction

[논문리뷰] STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer

August 15, 2025

Honghua Chen이 [arXiv]에 게시한 ‘STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Online Perception

[논문리뷰] STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer

August 15, 2025

Honghua Chen이 [arXiv]에 게시한 ‘STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

KVCache

[논문리뷰] STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer

August 15, 2025

Honghua Chen이 [arXiv]에 게시한 ‘STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cartoon Generation

[논문리뷰] ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing

August 15, 2025

Xiaoyu Li이 [arXiv]에 게시한 ‘ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Post-Keyframing

[논문리뷰] ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing

August 15, 2025

Xiaoyu Li이 [arXiv]에 게시한 ‘ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sparse Control

[논문리뷰] ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing

August 15, 2025

Xiaoyu Li이 [arXiv]에 게시한 ‘ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

UI Agent

[논문리뷰] UI-Venus Technical Report: Building High-performance UI Agents with RFT

August 15, 2025

Shuheng Shen이 [arXiv]에 게시한 ‘UI-Venus Technical Report: Building High-performance UI Agents with RFT’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

RFT

[논문리뷰] UI-Venus Technical Report: Building High-performance UI Agents with RFT

August 15, 2025

Shuheng Shen이 [arXiv]에 게시한 ‘UI-Venus Technical Report: Building High-performance UI Agents with RFT’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

UI Grounding

[논문리뷰] UI-Venus Technical Report: Building High-performance UI Agents with RFT

August 15, 2025

Shuheng Shen이 [arXiv]에 게시한 ‘UI-Venus Technical Report: Building High-performance UI Agents with RFT’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

UI Navigation

[논문리뷰] UI-Venus Technical Report: Building High-performance UI Agents with RFT

August 15, 2025

Shuheng Shen이 [arXiv]에 게시한 ‘UI-Venus Technical Report: Building High-performance UI Agents with RFT’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Cleaning

[논문리뷰] UI-Venus Technical Report: Building High-performance UI Agents with RFT

August 15, 2025

Shuheng Shen이 [arXiv]에 게시한 ‘UI-Venus Technical Report: Building High-performance UI Agents with RFT’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Evolving Trajectory

[논문리뷰] UI-Venus Technical Report: Building High-performance UI Agents with RFT

August 15, 2025

Shuheng Shen이 [arXiv]에 게시한 ‘UI-Venus Technical Report: Building High-performance UI Agents with RFT’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Mathematical Reasoning

[논문리뷰] We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning

August 15, 2025

Xiaowan Wang이 [arXiv]에 게시한 ‘We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Knowledge System

[논문리뷰] We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning

August 15, 2025

Xiaowan Wang이 [arXiv]에 게시한 ‘We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dataset Construction

[논문리뷰] We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning

August 15, 2025

Xiaowan Wang이 [arXiv]에 게시한 ‘We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mathematical Benchmark

[논문리뷰] We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning

August 15, 2025

Xiaowan Wang이 [arXiv]에 게시한 ‘We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Natural Language Processing (NLP)

[논문리뷰] When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing

August 15, 2025

Gjergji Kasneci이 [arXiv]에 게시한 ‘When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in...

Back to Top ↑

Post-hoc Explainability

[논문리뷰] When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing

August 15, 2025

Gjergji Kasneci이 [arXiv]에 게시한 ‘When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in...

Back to Top ↑

Differential Privacy (DP)

[논문리뷰] When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing

August 15, 2025

Gjergji Kasneci이 [arXiv]에 게시한 ‘When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in...

Back to Top ↑

Privacy-Utility Trade-off

[논문리뷰] When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing

August 15, 2025

Gjergji Kasneci이 [arXiv]에 게시한 ‘When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in...

Back to Top ↑

Model Faithfulness

[논문리뷰] When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing

August 15, 2025

Gjergji Kasneci이 [arXiv]에 게시한 ‘When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in...

Back to Top ↑

Text Privatization

[논문리뷰] When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing

August 15, 2025

Gjergji Kasneci이 [arXiv]에 게시한 ‘When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in...

Back to Top ↑

Reward Models

[논문리뷰] Controlling Multimodal LLMs via Reward-guided Decoding

August 18, 2025

Michal Drozdzal이 [arXiv]에 게시한 ‘Controlling Multimodal LLMs via Reward-guided Decoding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Guided Decoding

[논문리뷰] Controlling Multimodal LLMs via Reward-guided Decoding

August 18, 2025

Michal Drozdzal이 [arXiv]에 게시한 ‘Controlling Multimodal LLMs via Reward-guided Decoding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Object Precision

[논문리뷰] Controlling Multimodal LLMs via Reward-guided Decoding

August 18, 2025

Michal Drozdzal이 [arXiv]에 게시한 ‘Controlling Multimodal LLMs via Reward-guided Decoding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Object Recall

[논문리뷰] Controlling Multimodal LLMs via Reward-guided Decoding

August 18, 2025

Michal Drozdzal이 [arXiv]에 게시한 ‘Controlling Multimodal LLMs via Reward-guided Decoding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Inference-time Control

[논문리뷰] Controlling Multimodal LLMs via Reward-guided Decoding

August 18, 2025

Michal Drozdzal이 [arXiv]에 게시한 ‘Controlling Multimodal LLMs via Reward-guided Decoding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dense Feature Maps

[논문리뷰] DINOv3

August 18, 2025

Maxime Oquab이 [arXiv]에 게시한 ‘DINOv3’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gram Anchoring

[논문리뷰] DINOv3

August 18, 2025

Maxime Oquab이 [arXiv]에 게시한 ‘DINOv3’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Geospatial AI

[논문리뷰] DINOv3

August 18, 2025

Maxime Oquab이 [arXiv]에 게시한 ‘DINOv3’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Audio-Driven Animation

[논문리뷰] FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

August 18, 2025

Mu Xu이 [arXiv]에 게시한 ‘FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Objective Optimization

[논문리뷰] FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

August 18, 2025

Mu Xu이 [arXiv]에 게시한 ‘FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Timestep-Layer Adaptive

[논문리뷰] FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

August 18, 2025

Mu Xu이 [arXiv]에 게시한 ‘FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Masked Autoencoder

[논문리뷰] MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data

August 18, 2025

Nicolas Gonthier이 [arXiv]에 게시한 ‘MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Earth Observation

[논문리뷰] MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data

August 18, 2025

Nicolas Gonthier이 [arXiv]에 게시한 ‘MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multitemporal

[논문리뷰] MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data

August 18, 2025

Nicolas Gonthier이 [arXiv]에 게시한 ‘MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multispectral

[논문리뷰] MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data

August 18, 2025

Nicolas Gonthier이 [arXiv]에 게시한 ‘MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fusion Strategies

[논문리뷰] MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data

August 18, 2025

Nicolas Gonthier이 [arXiv]에 게시한 ‘MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Target Normalization

[논문리뷰] MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data

August 18, 2025

Nicolas Gonthier이 [arXiv]에 게시한 ‘MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

논문 검색

[논문리뷰] PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing

August 18, 2025

Xianpei Han이 [arXiv]에 게시한 ‘PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

계층적 인덱싱

[논문리뷰] PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing

August 18, 2025

Xianpei Han이 [arXiv]에 게시한 ‘PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

유연한 검색

[논문리뷰] PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing

August 18, 2025

Xianpei Han이 [arXiv]에 게시한 ‘PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

정보 추출

[논문리뷰] PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing

August 18, 2025

Xianpei Han이 [arXiv]에 게시한 ‘PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

뷰 인식

[논문리뷰] PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing

August 18, 2025

Xianpei Han이 [arXiv]에 게시한 ‘PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

강화 학습

[논문리뷰] PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing

August 18, 2025

Xianpei Han이 [arXiv]에 게시한 ‘PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semi-supervised Learning

[논문리뷰] SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation

August 18, 2025

Paolo Soda이 [arXiv]에 게시한 ‘SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GAN-based Methods

[논문리뷰] SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation

August 18, 2025

Paolo Soda이 [arXiv]에 게시한 ‘SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image-to-image Translation

[논문리뷰] SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation

August 18, 2025

Paolo Soda이 [arXiv]에 게시한 ‘SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Ensemble Learning

[논문리뷰] SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation

August 18, 2025

Paolo Soda이 [arXiv]에 게시한 ‘SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Search

[논문리뷰] SSRL: Self-Search Reinforcement Learning

August 18, 2025

Yanxu Chen이 [arXiv]에 게시한 ‘SSRL: Self-Search Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Morphable Model

[논문리뷰] StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation

August 18, 2025

Junyong Noh이 [arXiv]에 게시한 ‘StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Face Stylization

[논문리뷰] StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation

August 18, 2025

Junyong Noh이 [arXiv]에 게시한 ‘StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-to-Image Translation

[논문리뷰] StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation

August 18, 2025

Junyong Noh이 [arXiv]에 게시한 ‘StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Attribute Preservation

[논문리뷰] StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation

August 18, 2025

Junyong Noh이 [arXiv]에 게시한 ‘StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Dataset

[논문리뷰] TexVerse: A Universe of 3D Objects with High-Resolution Textures

August 18, 2025

Nan Cao이 [arXiv]에 게시한 ‘TexVerse: A Universe of 3D Objects with High-Resolution Textures’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

High-Resolution Textures

[논문리뷰] TexVerse: A Universe of 3D Objects with High-Resolution Textures

August 18, 2025

Nan Cao이 [arXiv]에 게시한 ‘TexVerse: A Universe of 3D Objects with High-Resolution Textures’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Physically Based Rendering (PBR)

[논문리뷰] TexVerse: A Universe of 3D Objects with High-Resolution Textures

August 18, 2025

Nan Cao이 [arXiv]에 게시한 ‘TexVerse: A Universe of 3D Objects with High-Resolution Textures’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Animation

[논문리뷰] TexVerse: A Universe of 3D Objects with High-Resolution Textures

August 18, 2025

Nan Cao이 [arXiv]에 게시한 ‘TexVerse: A Universe of 3D Objects with High-Resolution Textures’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GPT-5 Annotations

[논문리뷰] TexVerse: A Universe of 3D Objects with High-Resolution Textures

August 18, 2025

Nan Cao이 [arXiv]에 게시한 ‘TexVerse: A Universe of 3D Objects with High-Resolution Textures’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sketchfab

[논문리뷰] TexVerse: A Universe of 3D Objects with High-Resolution Textures

August 18, 2025

Nan Cao이 [arXiv]에 게시한 ‘TexVerse: A Universe of 3D Objects with High-Resolution Textures’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sandbox

[논문리뷰] Thyme: Think Beyond Images

August 18, 2025

Wei Chen이 [arXiv]에 게시한 ‘Thyme: Think Beyond Images’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Explanation

[논문리뷰] X-Node: Self-Explanation is All We Need

August 18, 2025

Islem Rekik이 [arXiv]에 게시한 ‘X-Node: Self-Explanation is All We Need’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Node Classification

[논문리뷰] X-Node: Self-Explanation is All We Need

August 18, 2025

Islem Rekik이 [arXiv]에 게시한 ‘X-Node: Self-Explanation is All We Need’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dynamic 3D

[논문리뷰] 4DNeX: Feed-Forward 4D Generative Modeling Made Easy

August 19, 2025

Zeng Tao이 [arXiv]에 게시한 ‘4DNeX: Feed-Forward 4D Generative Modeling Made Easy’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Single Image Input

[논문리뷰] 4DNeX: Feed-Forward 4D Generative Modeling Made Easy

August 19, 2025

Zeng Tao이 [arXiv]에 게시한 ‘4DNeX: Feed-Forward 4D Generative Modeling Made Easy’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Large Reasoning Models (LRMs)

[논문리뷰] Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information

August 19, 2025

Xi Yang이 [arXiv]에 게시한 ‘Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Incomplete Problems

[논문리뷰] Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information

August 19, 2025

Xi Yang이 [arXiv]에 게시한 ‘Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

CRITIC-math

[논문리뷰] Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information

August 19, 2025

Xi Yang이 [arXiv]에 게시한 ‘Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cognitive-Inspired RAG

[논문리뷰] ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning

August 19, 2025

Yufeng Wang이 [arXiv]에 게시한 ‘ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Stateful Reasoning

[논문리뷰] ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning

August 19, 2025

Yufeng Wang이 [arXiv]에 게시한 ‘ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long Narrative Comprehension

[논문리뷰] ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning

August 19, 2025

Yufeng Wang이 [arXiv]에 게시한 ‘ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dynamic Memory

[논문리뷰] ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning

August 19, 2025

Yufeng Wang이 [arXiv]에 게시한 ‘ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Metacognitive Regulation

[논문리뷰] ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning

August 19, 2025

Yufeng Wang이 [arXiv]에 게시한 ‘ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-step Retrieval

[논문리뷰] ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning

August 19, 2025

Yufeng Wang이 [arXiv]에 게시한 ‘ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hierarchical Knowledge Source

[논문리뷰] ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning

August 19, 2025

Yufeng Wang이 [arXiv]에 게시한 ‘ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Modal Fusion

[논문리뷰] G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration

August 19, 2025

Evgeny Burnaev이 [arXiv]에 게시한 ‘G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Prior Information

[논문리뷰] G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration

August 19, 2025

Evgeny Burnaev이 [arXiv]에 게시한 ‘G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spatial Intelligence

[논문리뷰] Has GPT-5 Achieved Spatial Intelligence? An Empirical Study

August 19, 2025

Ruisi Wang이 [arXiv]에 게시한 ‘Has GPT-5 Achieved Spatial Intelligence? An Empirical Study’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GPT-5

[논문리뷰] Has GPT-5 Achieved Spatial Intelligence? An Empirical Study

August 19, 2025

Ruisi Wang이 [arXiv]에 게시한 ‘Has GPT-5 Achieved Spatial Intelligence? An Empirical Study’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cognitive AI

[논문리뷰] Has GPT-5 Achieved Spatial Intelligence? An Empirical Study

August 19, 2025

Ruisi Wang이 [arXiv]에 게시한 ‘Has GPT-5 Achieved Spatial Intelligence? An Empirical Study’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Structured Reasoning

[논문리뷰] HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds

August 19, 2025

Artyom Sorokin이 [arXiv]에 게시한 ‘HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Virtual Worlds

[논문리뷰] HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds

August 19, 2025

Artyom Sorokin이 [arXiv]에 게시한 ‘HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

RPG

[논문리뷰] HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds

August 19, 2025

Artyom Sorokin이 [arXiv]에 게시한 ‘HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agent Systems

[논문리뷰] HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds

August 19, 2025

Artyom Sorokin이 [arXiv]에 게시한 ‘HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Combat Simulation

[논문리뷰] HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds

August 19, 2025

Artyom Sorokin이 [arXiv]에 게시한 ‘HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Alignment Pre-training

[논문리뷰] Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping

August 19, 2025

Tyler Derr이 [arXiv]에 게시한 ‘Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-to-Vision Mapping

[논문리뷰] Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping

August 19, 2025

Tyler Derr이 [arXiv]에 게시한 ‘Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Continuous Representations

[논문리뷰] Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping

August 19, 2025

Tyler Derr이 [arXiv]에 게시한 ‘Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Relighting

[논문리뷰] Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models

August 19, 2025

Zixiang Gao이 [arXiv]에 게시한 ‘Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Background Replacement

[논문리뷰] Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models

August 19, 2025

Zixiang Gao이 [arXiv]에 게시한 ‘Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Interactive Video Generation

[논문리뷰] Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model

August 19, 2025

Yifan Zhang이 [arXiv]에 게시한 ‘Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-Time AI

[논문리뷰] Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model

August 19, 2025

Yifan Zhang이 [arXiv]에 게시한 ‘Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Auto-Regressive Generation

[논문리뷰] Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model

August 19, 2025

Yifan Zhang이 [arXiv]에 게시한 ‘Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Pipeline

[논문리뷰] Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model

August 19, 2025

Yifan Zhang이 [arXiv]에 게시한 ‘Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Forcing

[논문리뷰] Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model

August 19, 2025

Yifan Zhang이 [arXiv]에 게시한 ‘Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

KV Caching

[논문리뷰] Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model

August 19, 2025

Yifan Zhang이 [arXiv]에 게시한 ‘Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Granularity Control

[논문리뷰] Next Visual Granularity Generation

August 19, 2025

Kang Liao이 [arXiv]에 게시한 ‘Next Visual Granularity Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Structured Representation

[논문리뷰] Next Visual Granularity Generation

August 19, 2025

Kang Liao이 [arXiv]에 게시한 ‘Next Visual Granularity Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hierarchical Generation

[논문리뷰] Next Visual Granularity Generation

August 19, 2025

Kang Liao이 [arXiv]에 게시한 ‘Next Visual Granularity Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Coarse-to-fine

[논문리뷰] Next Visual Granularity Generation

August 19, 2025

Kang Liao이 [arXiv]에 게시한 ‘Next Visual Granularity Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Tokenization

[논문리뷰] Next Visual Granularity Generation

August 19, 2025

Kang Liao이 [arXiv]에 게시한 ‘Next Visual Granularity Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Native Resolution Vision

[논문리뷰] Ovis2.5 Technical Report

August 19, 2025

Yang Li이 [arXiv]에 게시한 ‘Ovis2.5 Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Chart Analysis

[논문리뷰] Ovis2.5 Technical Report

August 19, 2025

Yang Li이 [arXiv]에 게시한 ‘Ovis2.5 Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Action-to-Video Generation

[논문리뷰] Precise Action-to-Video Generation Through Visual Action Prompts

August 19, 2025

Minghan Qin이 [arXiv]에 게시한 ‘Precise Action-to-Video Generation Through Visual Action Prompts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Action Prompts

[논문리뷰] Precise Action-to-Video Generation Through Visual Action Prompts

August 19, 2025

Minghan Qin이 [arXiv]에 게시한 ‘Precise Action-to-Video Generation Through Visual Action Prompts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Skeleton Representation

[논문리뷰] Precise Action-to-Video Generation Through Visual Action Prompts

August 19, 2025

Minghan Qin이 [arXiv]에 게시한 ‘Precise Action-to-Video Generation Through Visual Action Prompts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human-Object Interaction

[논문리뷰] Precise Action-to-Video Generation Through Visual Action Prompts

August 19, 2025

Minghan Qin이 [arXiv]에 게시한 ‘Precise Action-to-Video Generation Through Visual Action Prompts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-Domain Transfer

[논문리뷰] Precise Action-to-Video Generation Through Visual Action Prompts

August 19, 2025

Minghan Qin이 [arXiv]에 게시한 ‘Precise Action-to-Video Generation Through Visual Action Prompts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Rubric-based Reward

[논문리뷰] Reinforcement Learning with Rubric Anchors

August 19, 2025

Haokai Xu이 [arXiv]에 게시한 ‘Reinforcement Learning with Rubric Anchors’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

RLVR Extension

[논문리뷰] Reinforcement Learning with Rubric Anchors

August 19, 2025

Haokai Xu이 [arXiv]에 게시한 ‘Reinforcement Learning with Rubric Anchors’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human-centric AI

[논문리뷰] Reinforcement Learning with Rubric Anchors

August 19, 2025

Haokai Xu이 [arXiv]에 게시한 ‘Reinforcement Learning with Rubric Anchors’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reward Hacking Mitigation

[논문리뷰] Reinforcement Learning with Rubric Anchors

August 19, 2025

Haokai Xu이 [arXiv]에 게시한 ‘Reinforcement Learning with Rubric Anchors’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Speech Representation Learning

[논문리뷰] Representing Speech Through Autoregressive Prediction of Cochlear Tokens

August 19, 2025

Daniel L. K. Yamins이 [arXiv]에 게시한 ‘Representing Speech Through Autoregressive Prediction of Cochlear Tokens’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cochlear Tokens

[논문리뷰] Representing Speech Through Autoregressive Prediction of Cochlear Tokens

August 19, 2025

Daniel L. K. Yamins이 [arXiv]에 게시한 ‘Representing Speech Through Autoregressive Prediction of Cochlear Tokens’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Biologically Inspired AI

[논문리뷰] Representing Speech Through Autoregressive Prediction of Cochlear Tokens

August 19, 2025

Daniel L. K. Yamins이 [arXiv]에 게시한 ‘Representing Speech Through Autoregressive Prediction of Cochlear Tokens’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Audio Processing

[논문리뷰] Representing Speech Through Autoregressive Prediction of Cochlear Tokens

August 19, 2025

Daniel L. K. Yamins이 [arXiv]에 게시한 ‘Representing Speech Through Autoregressive Prediction of Cochlear Tokens’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Classifier-free Guidance

[논문리뷰] S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models

August 19, 2025

Meiqi Wu이 [arXiv]에 게시한 ‘S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Guidance

[논문리뷰] S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models

August 19, 2025

Meiqi Wu이 [arXiv]에 게시한 ‘S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Stochastic Block-Dropping

[논문리뷰] S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models

August 19, 2025

Meiqi Wu이 [arXiv]에 게시한 ‘S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Efficient Architectures

[논문리뷰] Speed Always Wins: A Survey on Efficient Architectures for Large Language Models

August 19, 2025

Jusen Du이 [arXiv]에 게시한 ‘Speed Always Wins: A Survey on Efficient Architectures for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Transformer Optimization

[논문리뷰] Speed Always Wins: A Survey on Efficient Architectures for Large Language Models

August 19, 2025

Jusen Du이 [arXiv]에 게시한 ‘Speed Always Wins: A Survey on Efficient Architectures for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Robustness

[논문리뷰] When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs

August 19, 2025

Elena Tutubalina이 [arXiv]에 게시한 ‘When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

In-Context Learning

[논문리뷰] When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs

August 19, 2025

Elena Tutubalina이 [arXiv]에 게시한 ‘When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Batch Calibration

[논문리뷰] When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs

August 19, 2025

Elena Tutubalina이 [arXiv]에 게시한 ‘When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Template Ensembles

[논문리뷰] When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs

August 19, 2025

Elena Tutubalina이 [arXiv]에 게시한 ‘When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Refinement

[논문리뷰] A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models

August 20, 2025

Zishang Jiang이 [arXiv]에 게시한 ‘A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Speech Separation

[논문리뷰] Advances in Speech Separation: Techniques, Challenges, and Future Trends

August 20, 2025

Zhuo Chen이 [arXiv]에 게시한 ‘Advances in Speech Separation: Techniques, Challenges, and Future Trends’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Deep Neural Networks

[논문리뷰] Advances in Speech Separation: Techniques, Challenges, and Future Trends

August 20, 2025

Zhuo Chen이 [arXiv]에 게시한 ‘Advances in Speech Separation: Techniques, Challenges, and Future Trends’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cocktail Party Problem

[논문리뷰] Advances in Speech Separation: Techniques, Challenges, and Future Trends

August 20, 2025

Zhuo Chen이 [arXiv]에 게시한 ‘Advances in Speech Separation: Techniques, Challenges, and Future Trends’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Unsupervised Learning

[논문리뷰] Advances in Speech Separation: Techniques, Challenges, and Future Trends

August 20, 2025

Zhuo Chen이 [arXiv]에 게시한 ‘Advances in Speech Separation: Techniques, Challenges, and Future Trends’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Datasets

[논문리뷰] Advances in Speech Separation: Techniques, Challenges, and Future Trends

August 20, 2025

Zhuo Chen이 [arXiv]에 게시한 ‘Advances in Speech Separation: Techniques, Challenges, and Future Trends’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Moral Reasoning

[논문리뷰] Beyond Human Judgment: A Bayesian Evaluation of LLMs’ Moral Values Understanding

August 20, 2025

Alina Landowska이 [arXiv]에 게시한 ‘Beyond Human Judgment: A Bayesian Evaluation of LLMs’ Moral Values Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bayesian Evaluation

[논문리뷰] Beyond Human Judgment: A Bayesian Evaluation of LLMs’ Moral Values Understanding

August 20, 2025

Alina Landowska이 [arXiv]에 게시한 ‘Beyond Human Judgment: A Bayesian Evaluation of LLMs’ Moral Values Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Soft Labels

[논문리뷰] Beyond Human Judgment: A Bayesian Evaluation of LLMs’ Moral Values Understanding

August 20, 2025

Alina Landowska이 [arXiv]에 게시한 ‘Beyond Human Judgment: A Bayesian Evaluation of LLMs’ Moral Values Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Agent Reinforcement Learning

[논문리뷰] CAMAR: Continuous Actions Multi-Agent Routing

August 20, 2025

Alexey Skrynnik이 [arXiv]에 게시한 ‘CAMAR: Continuous Actions Multi-Agent Routing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Continuous Control

[논문리뷰] CAMAR: Continuous Actions Multi-Agent Routing

August 20, 2025

Alexey Skrynnik이 [arXiv]에 게시한 ‘CAMAR: Continuous Actions Multi-Agent Routing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pathfinding

[논문리뷰] CAMAR: Continuous Actions Multi-Agent Routing

August 20, 2025

Alexey Skrynnik이 [arXiv]에 게시한 ‘CAMAR: Continuous Actions Multi-Agent Routing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

MARL Benchmark

[논문리뷰] CAMAR: Continuous Actions Multi-Agent Routing

August 20, 2025

Alexey Skrynnik이 [arXiv]에 게시한 ‘CAMAR: Continuous Actions Multi-Agent Routing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GPU Acceleration

[논문리뷰] CAMAR: Continuous Actions Multi-Agent Routing

August 20, 2025

Alexey Skrynnik이 [arXiv]에 게시한 ‘CAMAR: Continuous Actions Multi-Agent Routing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Heterogeneous Agents

[논문리뷰] CAMAR: Continuous Actions Multi-Agent Routing

August 20, 2025

Alexey Skrynnik이 [arXiv]에 게시한 ‘CAMAR: Continuous Actions Multi-Agent Routing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Chain-of-Agents

[논문리뷰] Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

August 20, 2025

Liam-Liu이 [arXiv]에 게시한 ‘Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agent Foundation Models

[논문리뷰] Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

August 20, 2025

Liam-Liu이 [arXiv]에 게시한 ‘Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-agent Distillation

[논문리뷰] Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

August 20, 2025

Liam-Liu이 [arXiv]에 게시한 ‘Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Copyright Protection

[논문리뷰] Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends

August 20, 2025

Xixiang Zhao이 [arXiv]에 게시한 ‘Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Fingerprinting

[논문리뷰] Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends

August 20, 2025

Xixiang Zhao이 [arXiv]에 게시한 ‘Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text Watermarking

[논문리뷰] Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends

August 20, 2025

Xixiang Zhao이 [arXiv]에 게시한 ‘Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Invasive Fingerprinting

[논문리뷰] Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends

August 20, 2025

Xixiang Zhao이 [arXiv]에 게시한 ‘Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Intrinsic Fingerprinting

[논문리뷰] Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends

August 20, 2025

Xixiang Zhao이 [arXiv]에 게시한 ‘Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Intellectual Property

[논문리뷰] Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends

August 20, 2025

Xixiang Zhao이 [arXiv]에 게시한 ‘Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Digital Rights Management

[논문리뷰] Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends

August 20, 2025

Xixiang Zhao이 [arXiv]에 게시한 ‘Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Backdoor Watermarking

[논문리뷰] Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends

August 20, 2025

Xixiang Zhao이 [arXiv]에 게시한 ‘Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sparse Autoencoders

[논문리뷰] CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Selection

August 20, 2025

Adriano Koshiyama이 [arXiv]에 게시한 ‘CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Select...

Back to Top ↑

LLM Steering

[논문리뷰] CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Selection

August 20, 2025

Adriano Koshiyama이 [arXiv]에 게시한 ‘CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Select...

Back to Top ↑

Feature Selection

[논문리뷰] CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Selection

August 20, 2025

Adriano Koshiyama이 [arXiv]에 게시한 ‘CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Select...

Back to Top ↑

Correlation Analysis

[논문리뷰] CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Selection

August 20, 2025

Adriano Koshiyama이 [arXiv]에 게시한 ‘CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Select...

Back to Top ↑

Video Recommendation

[논문리뷰] Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations

August 20, 2025

Mounia Lalmas이 [arXiv]에 게시한 ‘Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Content-Based Filtering

[논문리뷰] Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations

August 20, 2025

Mounia Lalmas이 [arXiv]에 게시한 ‘Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pointing

[논문리뷰] Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation

August 20, 2025

Fei Ni이 [arXiv]에 게시한 ‘Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Zero-shot Generalization

[논문리뷰] Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation

August 20, 2025

Fei Ni이 [arXiv]에 게시한 ‘Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Podcast Recommendation

[논문리뷰] Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge

August 20, 2025

Alice Wang이 [arXiv]에 게시한 ‘Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Offline Evaluation

[논문리뷰] Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge

August 20, 2025

Alice Wang이 [arXiv]에 게시한 ‘Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

User Profiling

[논문리뷰] Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge

August 20, 2025

Alice Wang이 [arXiv]에 게시한 ‘Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Affective Computing

[논문리뷰] Leveraging Large Language Models for Predictive Analysis of Human Misery

August 20, 2025

Abhilash Nandy이 [arXiv]에 게시한 ‘Leveraging Large Language Models for Predictive Analysis of Human Misery’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Misery Score Prediction

[논문리뷰] Leveraging Large Language Models for Predictive Analysis of Human Misery

August 20, 2025

Abhilash Nandy이 [arXiv]에 게시한 ‘Leveraging Large Language Models for Predictive Analysis of Human Misery’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gamified Evaluation

[논문리뷰] Leveraging Large Language Models for Predictive Analysis of Human Misery

August 20, 2025

Abhilash Nandy이 [arXiv]에 게시한 ‘Leveraging Large Language Models for Predictive Analysis of Human Misery’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Feedback-driven Adaptation

[논문리뷰] Leveraging Large Language Models for Predictive Analysis of Human Misery

August 20, 2025

Abhilash Nandy이 [arXiv]에 게시한 ‘Leveraging Large Language Models for Predictive Analysis of Human Misery’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Unposed Reconstruction

[논문리뷰] LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

August 20, 2025

Yen-Yu Lin이 [arXiv]에 게시한 ‘LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Incremental Optimization

[논문리뷰] LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

August 20, 2025

Yen-Yu Lin이 [arXiv]에 게시한 ‘LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Octree

[논문리뷰] LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

August 20, 2025

Yen-Yu Lin이 [arXiv]에 게시한 ‘LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long Videos

[논문리뷰] LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

August 20, 2025

Yen-Yu Lin이 [arXiv]에 게시한 ‘LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Browsing

[논문리뷰] MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents

August 20, 2025

Jun Dong이 [arXiv]에 게시한 ‘MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Audio Intelligence

[논문리뷰] MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence

August 20, 2025

Fernando López이 [arXiv]에 게시한 ‘MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long-Form Audio

[논문리뷰] MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence

August 20, 2025

Fernando López이 [arXiv]에 게시한 ‘MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multicultural Music

[논문리뷰] MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence

August 20, 2025

Fernando López이 [arXiv]에 게시한 ‘MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

SAM

[논문리뷰] MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation

August 20, 2025

Jonas Geiping이 [arXiv]에 게시한 ‘MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Zero-Order Optimization

[논문리뷰] MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation

August 20, 2025

Jonas Geiping이 [arXiv]에 게시한 ‘MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bayesian Optimization

[논문리뷰] MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation

August 20, 2025

Jonas Geiping이 [arXiv]에 게시한 ‘MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Confidence Estimation

[논문리뷰] Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation

August 20, 2025

Xinyi Wang이 [arXiv]에 게시한 ‘Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fine-Grained

[논문리뷰] Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation

August 20, 2025

Xinyi Wang이 [arXiv]에 게시한 ‘Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Monte Carlo Sampling

[논문리뷰] Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation

August 20, 2025

Xinyi Wang이 [arXiv]에 게시한 ‘Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Backward Confidence Integration

[논문리뷰] Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation

August 20, 2025

Xinyi Wang이 [arXiv]에 게시한 ‘Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Motion Transfer

[논문리뷰] Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence

August 20, 2025

Xin Chen이 [arXiv]에 게시한 ‘Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-topology

[논문리뷰] Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence

August 20, 2025

Xin Chen이 [arXiv]에 게시한 ‘Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sparse Correspondence

[논문리뷰] Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence

August 20, 2025

Xin Chen이 [arXiv]에 게시한 ‘Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Motion Matching

[논문리뷰] Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence

August 20, 2025

Xin Chen이 [arXiv]에 게시한 ‘Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Controllable Image Generation

[논문리뷰] MultiRef: Controllable Image Generation with Multiple Visual References

August 20, 2025

Shiyun Lang이 [arXiv]에 게시한 ‘MultiRef: Controllable Image Generation with Multiple Visual References’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-modal Generation

[논문리뷰] MultiRef: Controllable Image Generation with Multiple Visual References

August 20, 2025

Shiyun Lang이 [arXiv]에 게시한 ‘MultiRef: Controllable Image Generation with Multiple Visual References’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual References

[논문리뷰] MultiRef: Controllable Image Generation with Multiple Visual References

August 20, 2025

Shiyun Lang이 [arXiv]에 게시한 ‘MultiRef: Controllable Image Generation with Multiple Visual References’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image-to-Image

[논문리뷰] MultiRef: Controllable Image Generation with Multiple Visual References

August 20, 2025

Shiyun Lang이 [arXiv]에 게시한 ‘MultiRef: Controllable Image Generation with Multiple Visual References’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

MLLM-as-a-Judge

[논문리뷰] MultiRef: Controllable Image Generation with Multiple Visual References

August 20, 2025

Shiyun Lang이 [arXiv]에 게시한 ‘MultiRef: Controllable Image Generation with Multiple Visual References’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

ID Consistency

[논문리뷰] OmniTry: Virtual Try-On Anything without Masks

August 20, 2025

Xiaoduan Feng이 [arXiv]에 게시한 ‘OmniTry: Virtual Try-On Anything without Masks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Wearable Objects

[논문리뷰] OmniTry: Virtual Try-On Anything without Masks

August 20, 2025

Xiaoduan Feng이 [arXiv]에 게시한 ‘OmniTry: Virtual Try-On Anything without Masks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Markup Language

[논문리뷰] Prompt Orchestration Markup Language

August 20, 2025

Yuqing Yang이 [arXiv]에 게시한 ‘Prompt Orchestration Markup Language’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Structured Prompting

[논문리뷰] Prompt Orchestration Markup Language

August 20, 2025

Yuqing Yang이 [arXiv]에 게시한 ‘Prompt Orchestration Markup Language’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

IDE Support

[논문리뷰] Prompt Orchestration Markup Language

August 20, 2025

Yuqing Yang이 [arXiv]에 게시한 ‘Prompt Orchestration Markup Language’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Data

[논문리뷰] Prompt Orchestration Markup Language

August 20, 2025

Yuqing Yang이 [arXiv]에 게시한 ‘Prompt Orchestration Markup Language’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Styling System

[논문리뷰] Prompt Orchestration Markup Language

August 20, 2025

Yuqing Yang이 [arXiv]에 게시한 ‘Prompt Orchestration Markup Language’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Development Toolkit

[논문리뷰] Prompt Orchestration Markup Language

August 20, 2025

Yuqing Yang이 [arXiv]에 게시한 ‘Prompt Orchestration Markup Language’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Radiance Fields

[논문리뷰] Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research

August 20, 2025

Susanne Schmidt이 [arXiv]에 게시한 ‘Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

XR

[논문리뷰] Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research

August 20, 2025

Susanne Schmidt이 [arXiv]에 게시한 ‘Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

View Synthesis

[논문리뷰] Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research

August 20, 2025

Susanne Schmidt이 [arXiv]에 게시한 ‘Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Immersive Technology

[논문리뷰] Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research

August 20, 2025

Susanne Schmidt이 [arXiv]에 게시한 ‘Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Search and Recommendation

[논문리뷰] Semantic IDs for Joint Generative Search and Recommendation

August 20, 2025

Enrico Palumbo이 [arXiv]에 게시한 ‘Semantic IDs for Joint Generative Search and Recommendation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semantic IDs

[논문리뷰] Semantic IDs for Joint Generative Search and Recommendation

August 20, 2025

Enrico Palumbo이 [arXiv]에 게시한 ‘Semantic IDs for Joint Generative Search and Recommendation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bi-Encoder

[논문리뷰] Semantic IDs for Joint Generative Search and Recommendation

August 20, 2025

Enrico Palumbo이 [arXiv]에 게시한 ‘Semantic IDs for Joint Generative Search and Recommendation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human Preference Alignment

[논문리뷰] TempFlow-GRPO: When Timing Matters for GRPO in Flow Models

August 20, 2025

Jian Yang이 [arXiv]에 게시한 ‘TempFlow-GRPO: When Timing Matters for GRPO in Flow Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Temporal Credit Assignment

[논문리뷰] TempFlow-GRPO: When Timing Matters for GRPO in Flow Models

August 20, 2025

Jian Yang이 [arXiv]에 게시한 ‘TempFlow-GRPO: When Timing Matters for GRPO in Flow Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-Guided Editing

[논문리뷰] Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer

August 20, 2025

Deyu Zhou이 [arXiv]에 게시한 ‘Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Color Editing

[논문리뷰] Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer

August 20, 2025

Deyu Zhou이 [arXiv]에 게시한 ‘Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Modal AI

[논문리뷰] Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer

August 20, 2025

Deyu Zhou이 [arXiv]에 게시한 ‘Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image Manipulation

[논문리뷰] Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer

August 20, 2025

Deyu Zhou이 [arXiv]에 게시한 ‘Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Zero-shot HAR

[논문리뷰] ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents

August 20, 2025

Flora D. Salim이 [arXiv]에 게시한 ‘ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Time-Series Analysis

[논문리뷰] ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents

August 20, 2025

Flora D. Salim이 [arXiv]에 게시한 ‘ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Knowledge Base

[논문리뷰] ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents

August 20, 2025

Flora D. Salim이 [arXiv]에 게시한 ‘ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-sensor Fusion

[논문리뷰] ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents

August 20, 2025

Flora D. Salim이 [arXiv]에 게시한 ‘ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Verification

[논문리뷰] DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

August 21, 2025

Yu Lu이 [arXiv]에 게시한 ‘DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dual Learning

[논문리뷰] DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

August 21, 2025

Yu Lu이 [arXiv]에 게시한 ‘DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multilingual Translation

[논문리뷰] DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

August 21, 2025

Yu Lu이 [arXiv]에 게시한 ‘DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Autonomous Scientific Discovery

[논문리뷰] From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery

August 21, 2025

zijieqiu이 [arXiv]에 게시한 ‘From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scientific Workflow Automation

[논문리뷰] From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery

August 21, 2025

zijieqiu이 [arXiv]에 게시한 ‘From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Natural Sciences

[논문리뷰] From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery

August 21, 2025

zijieqiu이 [arXiv]에 게시한 ‘From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cognitive Diagnosis Model

[논문리뷰] From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models

August 21, 2025

Ziyan Kuang이 [arXiv]에 게시한 ‘From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Knowledge Assessment

[논문리뷰] From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models

August 21, 2025

Ziyan Kuang이 [arXiv]에 게시한 ‘From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Matrix Factorization

[논문리뷰] From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models

August 21, 2025

Ziyan Kuang이 [arXiv]에 게시한 ‘From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

CPA-QKA

[논문리뷰] From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models

August 21, 2025

Ziyan Kuang이 [arXiv]에 게시한 ‘From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Future Prediction

[논문리뷰] FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

August 21, 2025

tianlecai이 [arXiv]에 게시한 ‘FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dynamic Evaluation

[논문리뷰] FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

August 21, 2025

tianlecai이 [arXiv]에 게시한 ‘FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Financial Forecasting

[논문리뷰] FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

August 21, 2025

tianlecai이 [arXiv]에 게시한 ‘FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fully Homomorphic Encryption (FHE)

[논문리뷰] Leuvenshtein: Efficient FHE-based Edit Distance Computation with Single Bootstrap per Cell

August 21, 2025

Ingrid Verbauwhede이 [arXiv]에 게시한 ‘Leuvenshtein: Efficient FHE-based Edit Distance Computation with Single Bootstrap per Cell’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

TFHE

[논문리뷰] Leuvenshtein: Efficient FHE-based Edit Distance Computation with Single Bootstrap per Cell

August 21, 2025

Ingrid Verbauwhede이 [arXiv]에 게시한 ‘Leuvenshtein: Efficient FHE-based Edit Distance Computation with Single Bootstrap per Cell’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Levenshtein Distance

[논문리뷰] Leuvenshtein: Efficient FHE-based Edit Distance Computation with Single Bootstrap per Cell

August 21, 2025

Ingrid Verbauwhede이 [arXiv]에 게시한 ‘Leuvenshtein: Efficient FHE-based Edit Distance Computation with Single Bootstrap per Cell’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Programmable Bootstrapping (PBS)

[논문리뷰] Leuvenshtein: Efficient FHE-based Edit Distance Computation with Single Bootstrap per Cell

August 21, 2025

Ingrid Verbauwhede이 [arXiv]에 게시한 ‘Leuvenshtein: Efficient FHE-based Edit Distance Computation with Single Bootstrap per Cell’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Privacy-Preserving Computation

[논문리뷰] Leuvenshtein: Efficient FHE-based Edit Distance Computation with Single Bootstrap per Cell

August 21, 2025

Ingrid Verbauwhede이 [arXiv]에 게시한 ‘Leuvenshtein: Efficient FHE-based Edit Distance Computation with Single Bootstrap per Cell’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

String Similarity

[논문리뷰] Leuvenshtein: Efficient FHE-based Edit Distance Computation with Single Bootstrap per Cell

August 21, 2025

Ingrid Verbauwhede이 [arXiv]에 게시한 ‘Leuvenshtein: Efficient FHE-based Edit Distance Computation with Single Bootstrap per Cell’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scale Equivariance

[논문리뷰] Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer

August 21, 2025

Jeremiah Jiang이 [arXiv]에 게시한 ‘Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Deep Equilibrium Models

[논문리뷰] Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer

August 21, 2025

Jeremiah Jiang이 [arXiv]에 게시한 ‘Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Canonicalization

[논문리뷰] Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer

August 21, 2025

Jeremiah Jiang이 [arXiv]에 게시한 ‘Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image Classification

[논문리뷰] Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer

August 21, 2025

Jeremiah Jiang이 [arXiv]에 게시한 ‘Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semantic Segmentation

[논문리뷰] Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer

August 21, 2025

Jeremiah Jiang이 [arXiv]에 게시한 ‘Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Latent Representation

[논문리뷰] Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer

August 21, 2025

Jeremiah Jiang이 [arXiv]에 게시한 ‘Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Monotone Scaling

[논문리뷰] Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer

August 21, 2025

Jeremiah Jiang이 [arXiv]에 게시한 ‘Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Context Protocol

[논문리뷰] MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers

August 21, 2025

Prathyusha Jwalapuram이 [arXiv]에 게시한 ‘MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-World Applications

[논문리뷰] MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers

August 21, 2025

Prathyusha Jwalapuram이 [arXiv]에 게시한 ‘MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Unknown Tools

[논문리뷰] MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers

August 21, 2025

Prathyusha Jwalapuram이 [arXiv]에 게시한 ‘MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Structured Mesh

[논문리뷰] MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

August 21, 2025

Jiangmiao이 [arXiv]에 게시한 ‘MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Blender Python

[논문리뷰] MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

August 21, 2025

Jiangmiao이 [arXiv]에 게시한 ‘MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Shape Editing

[논문리뷰] MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

August 21, 2025

Jiangmiao이 [arXiv]에 게시한 ‘MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Part-based Representation

[논문리뷰] MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

August 21, 2025

Jiangmiao이 [arXiv]에 게시한 ‘MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hybrid Architecture

[논문리뷰] NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

August 21, 2025

abercovich이 [arXiv]에 게시한 ‘NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mamba-Transformer

[논문리뷰] NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

August 21, 2025

abercovich이 [arXiv]에 게시한 ‘NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning LLM

[논문리뷰] NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

August 21, 2025

abercovich이 [arXiv]에 게시한 ‘NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

High Throughput

[논문리뷰] NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

August 21, 2025

abercovich이 [arXiv]에 게시한 ‘NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

On-Policy RL

[논문리뷰] On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

August 21, 2025

Guoyin Wang이 [arXiv]에 게시한 ‘On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting’ 논문에 대한...

Back to Top ↑

Off-Policy Experts

[논문리뷰] On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

August 21, 2025

Guoyin Wang이 [arXiv]에 게시한 ‘On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting’ 논문에 대한...

Back to Top ↑

Dynamic Weighting

[논문리뷰] On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

August 21, 2025

Guoyin Wang이 [arXiv]에 게시한 ‘On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting’ 논문에 대한...

Back to Top ↑

Post-training Quantization (PTQ)

[논문리뷰] Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs

August 21, 2025

Haobo Xu이 [arXiv]에 게시한 ‘Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Activation Outliers

[논문리뷰] Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs

August 21, 2025

Haobo Xu이 [arXiv]에 게시한 ‘Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Quantization Methods

[논문리뷰] Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs

August 21, 2025

Haobo Xu이 [arXiv]에 게시한 ‘Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Efficient Deployment

[논문리뷰] Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs

August 21, 2025

Haobo Xu이 [arXiv]에 게시한 ‘Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-modal Recommendation

[논문리뷰] Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation

August 21, 2025

Shiqing Wu이 [arXiv]에 게시한 ‘Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Graph Neural Network

[논문리뷰] Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation

August 21, 2025

Shiqing Wu이 [arXiv]에 게시한 ‘Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Homography Relations

[논문리뷰] Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation

August 21, 2025

Shiqing Wu이 [arXiv]에 게시한 ‘Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Meta-network

[논문리뷰] Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation

August 21, 2025

Shiqing Wu이 [arXiv]에 게시한 ‘Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Orthogonal Constraint

[논문리뷰] Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation

August 21, 2025

Shiqing Wu이 [arXiv]에 게시한 ‘Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Sparsity

[논문리뷰] Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation

August 21, 2025

Shiqing Wu이 [arXiv]에 게시한 ‘Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Embodied Cognition

[논문리뷰] RynnEC: Bringing MLLMs into Embodied World

August 21, 2025

jiangpinliu이 [arXiv]에 게시한 ‘RynnEC: Bringing MLLMs into Embodied World’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sparse Input

[논문리뷰] Tinker: Diffusion’s Gift to 3D–Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization

August 21, 2025

Hao Chen이 [arXiv]에 게시한 ‘Tinker: Diffusion’s Gift to 3D–Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scene Completion

[논문리뷰] Tinker: Diffusion’s Gift to 3D–Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization

August 21, 2025

Hao Chen이 [arXiv]에 게시한 ‘Tinker: Diffusion’s Gift to 3D–Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vision Language Models

[논문리뷰] ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?

August 21, 2025

Daeyoung Kim이 [arXiv]에 게시한 ‘ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vietnamese Language

[논문리뷰] ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?

August 21, 2025

Daeyoung Kim이 [arXiv]에 게시한 ‘ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-Lingual Reasoning

[논문리뷰] ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?

August 21, 2025

Daeyoung Kim이 [arXiv]에 게시한 ‘ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

ViExam

[논문리뷰] ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?

August 21, 2025

Daeyoung Kim이 [arXiv]에 게시한 ‘ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multilingual Benchmark

[논문리뷰] mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning

August 21, 2025

anoperson이 [arXiv]에 게시한 ‘mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning Taxonomy

[논문리뷰] mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning

August 21, 2025

anoperson이 [arXiv]에 게시한 ‘mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Benchmark Scaling

[논문리뷰] mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning

August 21, 2025

anoperson이 [arXiv]에 게시한 ‘mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cultural Nuances

[논문리뷰] mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning

August 21, 2025

anoperson이 [arXiv]에 게시한 ‘mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Parametric Human Model

[논문리뷰] ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling

August 22, 2025

Shunsuke Saito이 [arXiv]에 게시한 ‘ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Human Modeling

[논문리뷰] ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling

August 22, 2025

Shunsuke Saito이 [arXiv]에 게시한 ‘ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Shape-Skeleton Decoupling

[논문리뷰] ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling

August 22, 2025

Shunsuke Saito이 [arXiv]에 게시한 ‘ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pose Correctives

[논문리뷰] ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling

August 22, 2025

Shunsuke Saito이 [arXiv]에 게시한 ‘ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Single Image Mesh Fitting

[논문리뷰] ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling

August 22, 2025

Shunsuke Saito이 [arXiv]에 게시한 ‘ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Expressive Modeling

[논문리뷰] ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling

August 22, 2025

Shunsuke Saito이 [arXiv]에 게시한 ‘ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Goliath Dataset

[논문리뷰] ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling

August 22, 2025

Shunsuke Saito이 [arXiv]에 게시한 ‘ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Benchmarks

[논문리뷰] A Survey on Large Language Model Benchmarks

August 22, 2025

Siyi Li이 [arXiv]에 게시한 ‘A Survey on Large Language Model Benchmarks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

General Capabilities

[논문리뷰] A Survey on Large Language Model Benchmarks

August 22, 2025

Siyi Li이 [arXiv]에 게시한 ‘A Survey on Large Language Model Benchmarks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Domain-Specific Benchmarks

[논문리뷰] A Survey on Large Language Model Benchmarks

August 22, 2025

Siyi Li이 [arXiv]에 게시한 ‘A Survey on Large Language Model Benchmarks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Target-Specific Benchmarks

[논문리뷰] A Survey on Large Language Model Benchmarks

August 22, 2025

Siyi Li이 [arXiv]에 게시한 ‘A Survey on Large Language Model Benchmarks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Confidence Filtering

[논문리뷰] Deep Think with Confidence

August 22, 2025

Xuewei Wang이 [arXiv]에 게시한 ‘Deep Think with Confidence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Consistency

[논문리뷰] Deep Think with Confidence

August 22, 2025

Xuewei Wang이 [arXiv]에 게시한 ‘Deep Think with Confidence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Early Stopping

[논문리뷰] Deep Think with Confidence

August 22, 2025

Xuewei Wang이 [arXiv]에 게시한 ‘Deep Think with Confidence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Majority Voting

[논문리뷰] Deep Think with Confidence

August 22, 2025

Xuewei Wang이 [arXiv]에 게시한 ‘Deep Think with Confidence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Domain Specialization

[논문리뷰] Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models

August 22, 2025

Lifan Guo이 [arXiv]에 게시한 ‘Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Best-of-N Selection

[논문리뷰] Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models

August 22, 2025

Lifan Guo이 [arXiv]에 게시한 ‘Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AI Companionship

[논문리뷰] INTIMA: A Benchmark for Human-AI Companionship Behavior

August 22, 2025

Yacine Jernite이 [arXiv]에 게시한 ‘INTIMA: A Benchmark for Human-AI Companionship Behavior’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human-AI Interaction

[논문리뷰] INTIMA: A Benchmark for Human-AI Companionship Behavior

August 22, 2025

Yacine Jernite이 [arXiv]에 게시한 ‘INTIMA: A Benchmark for Human-AI Companionship Behavior’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Emotional AI

[논문리뷰] INTIMA: A Benchmark for Human-AI Companionship Behavior

August 22, 2025

Yacine Jernite이 [arXiv]에 게시한 ‘INTIMA: A Benchmark for Human-AI Companionship Behavior’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Boundary Setting

[논문리뷰] INTIMA: A Benchmark for Human-AI Companionship Behavior

August 22, 2025

Yacine Jernite이 [arXiv]에 게시한 ‘INTIMA: A Benchmark for Human-AI Companionship Behavior’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Psychological Frameworks

[논문리뷰] INTIMA: A Benchmark for Human-AI Companionship Behavior

August 22, 2025

Yacine Jernite이 [arXiv]에 게시한 ‘INTIMA: A Benchmark for Human-AI Companionship Behavior’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Foundation Model

[논문리뷰] Intern-S1: A Scientific Multimodal Foundation Model

August 22, 2025

xuhuang87이 [arXiv]에 게시한 ‘Intern-S1: A Scientific Multimodal Foundation Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scientific AI

[논문리뷰] Intern-S1: A Scientific Multimodal Foundation Model

August 22, 2025

xuhuang87이 [arXiv]에 게시한 ‘Intern-S1: A Scientific Multimodal Foundation Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dynamic Tokenizer

[논문리뷰] Intern-S1: A Scientific Multimodal Foundation Model

August 22, 2025

xuhuang87이 [arXiv]에 게시한 ‘Intern-S1: A Scientific Multimodal Foundation Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Low-Resource Learning

[논문리뷰] Intern-S1: A Scientific Multimodal Foundation Model

August 22, 2025

xuhuang87이 [arXiv]에 게시한 ‘Intern-S1: A Scientific Multimodal Foundation Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-world Tasks

[논문리뷰] LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries

August 22, 2025

huuuyeah이 [arXiv]에 게시한 ‘LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Error Analysis

[논문리뷰] LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries

August 22, 2025

huuuyeah이 [arXiv]에 게시한 ‘LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Foundational Models

[논문리뷰] Mobile-Agent-v3: Foundamental Agents for GUI Automation

August 22, 2025

Haowei Liu이 [arXiv]에 게시한 ‘Mobile-Agent-v3: Foundamental Agents for GUI Automation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-Platform

[논문리뷰] Mobile-Agent-v3: Foundamental Agents for GUI Automation

August 22, 2025

Haowei Liu이 [arXiv]에 게시한 ‘Mobile-Agent-v3: Foundamental Agents for GUI Automation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Single-Image Input

[논문리뷰] SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass

August 22, 2025

Ya Zhang이 [arXiv]에 게시한 ‘SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Feedforward Networks

[논문리뷰] SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass

August 22, 2025

Ya Zhang이 [arXiv]에 게시한 ‘SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Geometric Modeling

[논문리뷰] SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass

August 22, 2025

Ya Zhang이 [arXiv]에 게시한 ‘SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Texture Synthesis

[논문리뷰] SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass

August 22, 2025

Ya Zhang이 [arXiv]에 게시한 ‘SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Feature Aggregation

[논문리뷰] SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass

August 22, 2025

Ya Zhang이 [arXiv]에 게시한 ‘SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Human Reconstruction

[논문리뷰] Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds

August 22, 2025

Chuiyun Wu이 [arXiv]에 게시한 ‘Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Two-Image Input

[논문리뷰] Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds

August 22, 2025

Chuiyun Wu이 [arXiv]에 게시한 ‘Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-time Inference

[논문리뷰] Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds

August 22, 2025

Chuiyun Wu이 [arXiv]에 게시한 ‘Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Point Cloud Prediction

[논문리뷰] Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds

August 22, 2025

Chuiyun Wu이 [arXiv]에 게시한 ‘Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Feed-forward Network

[논문리뷰] Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds

August 22, 2025

Chuiyun Wu이 [arXiv]에 게시한 ‘Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Super-Resolution

[논문리뷰] Waver: Wave Your Way to Lifelike Video Generation

August 22, 2025

Yifu Zhang이 [arXiv]에 게시한 ‘Waver: Wave Your Way to Lifelike Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video-LLM

[논문리뷰] When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding

August 22, 2025

Rui Guo이 [arXiv]에 게시한 ‘When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Object Segmentation

[논문리뷰] When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding

August 22, 2025

Rui Guo이 [arXiv]에 게시한 ‘When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Open Access

[논문리뷰] aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists

August 22, 2025

Heng Zhang이 [arXiv]에 게시한 ‘aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Prompt Injection

[논문리뷰] aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists

August 22, 2025

Heng Zhang이 [arXiv]에 게시한 ‘aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Competitive Programming

[논문리뷰] AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions

August 25, 2025

Yidi Du이 [arXiv]에 게시한 ‘AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Test Case Generation

[논문리뷰] AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions

August 25, 2025

Yidi Du이 [arXiv]에 게시한 ‘AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Programming Competitions

[논문리뷰] AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions

August 25, 2025

Yidi Du이 [arXiv]에 게시한 ‘AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Algorithmic Problems

[논문리뷰] AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions

August 25, 2025

Yidi Du이 [arXiv]에 게시한 ‘AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agentic Applications

[논문리뷰] AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications

August 25, 2025

Liuyi Yao이 [arXiv]에 게시한 ‘AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

ReAct Paradigm

[논문리뷰] AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications

August 25, 2025

Liuyi Yao이 [arXiv]에 게시한 ‘AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Developer Experience

[논문리뷰] AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications

August 25, 2025

Liuyi Yao이 [arXiv]에 게시한 ‘AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Variational Problem Synthesis

[논문리뷰] Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

August 25, 2025

Ying Nian Wu이 [arXiv]에 게시한 ‘Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Policy Entropy

[논문리뷰] Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

August 25, 2025

Ying Nian Wu이 [arXiv]에 게시한 ‘Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning Benchmarks

[논문리뷰] Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

August 25, 2025

Ying Nian Wu이 [arXiv]에 게시한 ‘Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Annotated Data

[논문리뷰] CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning

August 25, 2025

Yulun Zhang이 [arXiv]에 게시한 ‘CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning’ 논문에 대한 자세한 리뷰...

Back to Top ↑

Model Stability

[논문리뷰] CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning

August 25, 2025

Yulun Zhang이 [arXiv]에 게시한 ‘CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning’ 논문에 대한 자세한 리뷰...

Back to Top ↑

Concept Unlearning

[논문리뷰] CRISP: Persistent Concept Unlearning via Sparse Autoencoders

August 25, 2025

Yonatan Belinkov이 [arXiv]에 게시한 ‘CRISP: Persistent Concept Unlearning via Sparse Autoencoders’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sparse Autoencoders (SAEs)

[논문리뷰] CRISP: Persistent Concept Unlearning via Sparse Autoencoders

August 25, 2025

Yonatan Belinkov이 [arXiv]에 게시한 ‘CRISP: Persistent Concept Unlearning via Sparse Autoencoders’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Interpretability

[논문리뷰] CRISP: Persistent Concept Unlearning via Sparse Autoencoders

August 25, 2025

Yonatan Belinkov이 [arXiv]에 게시한 ‘CRISP: Persistent Concept Unlearning via Sparse Autoencoders’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Safety-Critical AI

[논문리뷰] CRISP: Persistent Concept Unlearning via Sparse Autoencoders

August 25, 2025

Yonatan Belinkov이 [arXiv]에 게시한 ‘CRISP: Persistent Concept Unlearning via Sparse Autoencoders’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Feature Suppression

[논문리뷰] CRISP: Persistent Concept Unlearning via Sparse Autoencoders

August 25, 2025

Yonatan Belinkov이 [arXiv]에 게시한 ‘CRISP: Persistent Concept Unlearning via Sparse Autoencoders’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

WMDP Benchmark

[논문리뷰] CRISP: Persistent Concept Unlearning via Sparse Autoencoders

August 25, 2025

Yonatan Belinkov이 [arXiv]에 게시한 ‘CRISP: Persistent Concept Unlearning via Sparse Autoencoders’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

False Premise Detection

[논문리뷰] Do What? Teaching Vision-Language-Action Models to Reject the Impossible

August 25, 2025

Roei Herzig이 [arXiv]에 게시한 ‘Do What? Teaching Vision-Language-Action Models to Reject the Impossible’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Clarification

[논문리뷰] Do What? Teaching Vision-Language-Action Models to Reject the Impossible

August 25, 2025

Roei Herzig이 [arXiv]에 게시한 ‘Do What? Teaching Vision-Language-Action Models to Reject the Impossible’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Egocentric Video Generation

[논문리뷰] EgoTwin: Dreaming Body and View in First Person

August 25, 2025

Wentao Wang이 [arXiv]에 게시한 ‘EgoTwin: Dreaming Body and View in First Person’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Viewpoint Alignment

[논문리뷰] EgoTwin: Dreaming Body and View in First Person

August 25, 2025

Wentao Wang이 [arXiv]에 게시한 ‘EgoTwin: Dreaming Body and View in First Person’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Causal Interplay

[논문리뷰] EgoTwin: Dreaming Body and View in First Person

August 25, 2025

Wentao Wang이 [arXiv]에 게시한 ‘EgoTwin: Dreaming Body and View in First Person’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

First-Person Vision

[논문리뷰] EgoTwin: Dreaming Body and View in First Person

August 25, 2025

Wentao Wang이 [arXiv]에 게시한 ‘EgoTwin: Dreaming Body and View in First Person’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agentic RAG

[논문리뷰] End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning

August 25, 2025

Pengcheng Qiu이 [arXiv]에 게시한 ‘End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Traceable AI

[논문리뷰] End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning

August 25, 2025

Pengcheng Qiu이 [arXiv]에 게시한 ‘End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human Reasoning Styles

[논문리뷰] InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles

August 25, 2025

Diping Song이 [arXiv]에 게시한 ‘InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Social Deduction Games

[논문리뷰] InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles

August 25, 2025

Diping Song이 [arXiv]에 게시한 ‘InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Theory of Mind

[논문리뷰] InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles

August 25, 2025

Diping Song이 [arXiv]에 게시한 ‘InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Avalon Game

[논문리뷰] InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles

August 25, 2025

Diping Song이 [arXiv]에 게시한 ‘InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cognitive Grounding

[논문리뷰] InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles

August 25, 2025

Diping Song이 [arXiv]에 게시한 ‘InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Jailbreaking

[논문리뷰] Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts

August 25, 2025

Liming Fang이 [arXiv]에 게시한 ‘Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Red Teaming

[논문리뷰] Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts

August 25, 2025

Liming Fang이 [arXiv]에 게시한 ‘Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Malicious Content Detection

[논문리뷰] Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts

August 25, 2025

Liming Fang이 [arXiv]에 게시한 ‘Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Developer Messages

[논문리뷰] Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts

August 25, 2025

Liming Fang이 [arXiv]에 게시한 ‘Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

D-Attack

[논문리뷰] Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts

August 25, 2025

Liming Fang이 [arXiv]에 게시한 ‘Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

DH-CoT

[논문리뷰] Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts

August 25, 2025

Liming Fang이 [arXiv]에 게시한 ‘Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adversarial Attacks

[논문리뷰] Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts

August 25, 2025

Liming Fang이 [arXiv]에 게시한 ‘Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dataset Cleaning

[논문리뷰] Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts

August 25, 2025

Liming Fang이 [arXiv]에 게시한 ‘Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Inverse Kinematics

[논문리뷰] Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics

August 25, 2025

Xiao Sun이 [arXiv]에 게시한 ‘Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human Pose Estimation

[논문리뷰] Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics

August 25, 2025

Xiao Sun이 [arXiv]에 게시한 ‘Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

SMPL Model

[논문리뷰] Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics

August 25, 2025

Xiao Sun이 [arXiv]에 게시한 ‘Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Optimization-Free

[논문리뷰] Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics

August 25, 2025

Xiao Sun이 [arXiv]에 게시한 ‘Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data-Driven

[논문리뷰] Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics

August 25, 2025

Xiao Sun이 [arXiv]에 게시한 ‘Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Weakly Supervised Learning

[논문리뷰] Selective Contrastive Learning for Weakly Supervised Affordance Grounding

August 25, 2025

Jae-Pil Heo이 [arXiv]에 게시한 ‘Selective Contrastive Learning for Weakly Supervised Affordance Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Affordance Grounding

[논문리뷰] Selective Contrastive Learning for Weakly Supervised Affordance Grounding

August 25, 2025

Jae-Pil Heo이 [arXiv]에 게시한 ‘Selective Contrastive Learning for Weakly Supervised Affordance Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Part Discovery

[논문리뷰] Selective Contrastive Learning for Weakly Supervised Affordance Grounding

August 25, 2025

Jae-Pil Heo이 [arXiv]에 게시한 ‘Selective Contrastive Learning for Weakly Supervised Affordance Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Object Localization

[논문리뷰] Selective Contrastive Learning for Weakly Supervised Affordance Grounding

August 25, 2025

Jae-Pil Heo이 [arXiv]에 게시한 ‘Selective Contrastive Learning for Weakly Supervised Affordance Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

DINO

[논문리뷰] Selective Contrastive Learning for Weakly Supervised Affordance Grounding

August 25, 2025

Jae-Pil Heo이 [arXiv]에 게시한 ‘Selective Contrastive Learning for Weakly Supervised Affordance Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning Depth

[논문리뷰] Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling

August 26, 2025

Daniil Orel이 [arXiv]에 게시한 ‘Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cellular Automata

[논문리뷰] Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling

August 26, 2025

Daniil Orel이 [arXiv]에 게시한 ‘Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Recurrence

[논문리뷰] Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling

August 26, 2025

Daniil Orel이 [arXiv]에 게시한 ‘Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adaptive Computation Time

[논문리뷰] Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling

August 26, 2025

Daniil Orel이 [arXiv]에 게시한 ‘Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Exploration Bottleneck

[논문리뷰] Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning

August 26, 2025

Jiale Zhao이 [arXiv]에 게시한 ‘Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Instructional Scaffolding

[논문리뷰] Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning

August 26, 2025

Jiale Zhao이 [arXiv]에 게시한 ‘Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Rubric-based Rewards

[논문리뷰] Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning

August 26, 2025

Jiale Zhao이 [arXiv]에 게시한 ‘Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

General Reasoning

[논문리뷰] Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning

August 26, 2025

Jiale Zhao이 [arXiv]에 게시한 ‘Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

RL with Verifiable Rewards

[논문리뷰] Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning

August 26, 2025

Jiale Zhao이 [arXiv]에 게시한 ‘Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Compositional Visual Reasoning

[논문리뷰] Explain Before You Answer: A Survey on Compositional Visual Reasoning

August 26, 2025

Xin Zheng이 [arXiv]에 게시한 ‘Explain Before You Answer: A Survey on Compositional Visual Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Tool Learning

[논문리뷰] Explain Before You Answer: A Survey on Compositional Visual Reasoning

August 26, 2025

Xin Zheng이 [arXiv]에 게시한 ‘Explain Before You Answer: A Survey on Compositional Visual Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text Simplification

[논문리뷰] German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German

August 26, 2025

Cristian-George Craciun이 [arXiv]에 게시한 ‘German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Readability Control

[논문리뷰] German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German

August 26, 2025

Cristian-George Craciun이 [arXiv]에 게시한 ‘German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

German NLP

[논문리뷰] German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German

August 26, 2025

Cristian-George Craciun이 [arXiv]에 게시한 ‘German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Distillation

[논문리뷰] German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German

August 26, 2025

Cristian-George Craciun이 [arXiv]에 게시한 ‘German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-level Text Generation

[논문리뷰] German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German

August 26, 2025

Cristian-George Craciun이 [arXiv]에 게시한 ‘German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Versatility

[논문리뷰] InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

August 26, 2025

jinglinglin이 [arXiv]에 게시한 ‘InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Softmax

[논문리뷰] Limitations of Normalization in Attention Mechanism

August 26, 2025

Radu State이 [arXiv]에 게시한 ‘Limitations of Normalization in Attention Mechanism’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gradient Sensitivity

[논문리뷰] Limitations of Normalization in Attention Mechanism

August 26, 2025

Radu State이 [arXiv]에 게시한 ‘Limitations of Normalization in Attention Mechanism’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Token Separability

[논문리뷰] Limitations of Normalization in Attention Mechanism

August 26, 2025

Radu State이 [arXiv]에 게시한 ‘Limitations of Normalization in Attention Mechanism’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GPT-2

[논문리뷰] Limitations of Normalization in Attention Mechanism

August 26, 2025

Radu State이 [arXiv]에 게시한 ‘Limitations of Normalization in Attention Mechanism’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Language Models

[논문리뷰] MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment

August 26, 2025

Doratossadat Dastgheib이 [arXiv]에 게시한 ‘MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multilingual Benchmarking

[논문리뷰] MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment

August 26, 2025

Doratossadat Dastgheib이 [arXiv]에 게시한 ‘MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Persian Language

[논문리뷰] MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment

August 26, 2025

Doratossadat Dastgheib이 [arXiv]에 게시한 ‘MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cultural Nuance

[논문리뷰] MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment

August 26, 2025

Doratossadat Dastgheib이 [arXiv]에 게시한 ‘MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multiview Diffusion

[논문리뷰] MV-RAG: Retrieval Augmented Multiview Diffusion

August 26, 2025

sagiebenaim이 [arXiv]에 게시한 ‘MV-RAG: Retrieval Augmented Multiview Diffusion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Out-of-Domain

[논문리뷰] MV-RAG: Retrieval Augmented Multiview Diffusion

August 26, 2025

sagiebenaim이 [arXiv]에 게시한 ‘MV-RAG: Retrieval Augmented Multiview Diffusion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image Retrieval

[논문리뷰] MV-RAG: Retrieval Augmented Multiview Diffusion

August 26, 2025

sagiebenaim이 [arXiv]에 게시한 ‘MV-RAG: Retrieval Augmented Multiview Diffusion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hybrid Training

[논문리뷰] MV-RAG: Retrieval Augmented Multiview Diffusion

August 26, 2025

sagiebenaim이 [arXiv]에 게시한 ‘MV-RAG: Retrieval Augmented Multiview Diffusion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sparse-View

[논문리뷰] MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting

August 26, 2025

Yanzhe Liang이 [arXiv]에 게시한 ‘MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

2DGS

[논문리뷰] MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting

August 26, 2025

Yanzhe Liang이 [arXiv]에 게시한 ‘MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Generalizable

[논문리뷰] MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting

August 26, 2025

Yanzhe Liang이 [arXiv]에 게시한 ‘MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mesh Extraction

[논문리뷰] MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting

August 26, 2025

Yanzhe Liang이 [arXiv]에 게시한 ‘MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLMs as Judges

[논문리뷰] Neither Valid nor Reliable? Investigating the Use of LLMs as Judges

August 26, 2025

Golnoosh Farnadi이 [arXiv]에 게시한 ‘Neither Valid nor Reliable? Investigating the Use of LLMs as Judges’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

NLG Evaluation

[논문리뷰] Neither Valid nor Reliable? Investigating the Use of LLMs as Judges

August 26, 2025

Golnoosh Farnadi이 [arXiv]에 게시한 ‘Neither Valid nor Reliable? Investigating the Use of LLMs as Judges’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Measurement Theory

[논문리뷰] Neither Valid nor Reliable? Investigating the Use of LLMs as Judges

August 26, 2025

Golnoosh Farnadi이 [arXiv]에 게시한 ‘Neither Valid nor Reliable? Investigating the Use of LLMs as Judges’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Validity

[논문리뷰] Neither Valid nor Reliable? Investigating the Use of LLMs as Judges

August 26, 2025

Golnoosh Farnadi이 [arXiv]에 게시한 ‘Neither Valid nor Reliable? Investigating the Use of LLMs as Judges’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reliability

[논문리뷰] Neither Valid nor Reliable? Investigating the Use of LLMs as Judges

August 26, 2025

Golnoosh Farnadi이 [arXiv]에 게시한 ‘Neither Valid nor Reliable? Investigating the Use of LLMs as Judges’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Evaluation Bias

[논문리뷰] Neither Valid nor Reliable? Investigating the Use of LLMs as Judges

August 26, 2025

Golnoosh Farnadi이 [arXiv]에 게시한 ‘Neither Valid nor Reliable? Investigating the Use of LLMs as Judges’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Responsible AI

[논문리뷰] Neither Valid nor Reliable? Investigating the Use of LLMs as Judges

August 26, 2025

Golnoosh Farnadi이 [arXiv]에 게시한 ‘Neither Valid nor Reliable? Investigating the Use of LLMs as Judges’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Agent LLMs

[논문리뷰] PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs

August 26, 2025

Chenyu You이 [arXiv]에 게시한 ‘PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Academic Poster Generation

[논문리뷰] PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs

August 26, 2025

Chenyu You이 [arXiv]에 게시한 ‘PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Aesthetic Design

[논문리뷰] PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs

August 26, 2025

Chenyu You이 [arXiv]에 게시한 ‘PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Layout Optimization

[논문리뷰] PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs

August 26, 2025

Chenyu You이 [arXiv]에 게시한 ‘PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Typography

[논문리뷰] PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs

August 26, 2025

Chenyu You이 [arXiv]에 게시한 ‘PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Color Palette

[논문리뷰] PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs

August 26, 2025

Chenyu You이 [arXiv]에 게시한 ‘PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

VLM-as-Judge

[논문리뷰] PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs

August 26, 2025

Chenyu You이 [arXiv]에 게시한 ‘PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Content Fidelity

[논문리뷰] PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs

August 26, 2025

Chenyu You이 [arXiv]에 게시한 ‘PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semi-structured Tables

[논문리뷰] ST-Raptor: LLM-Powered Semi-Structured Table Question Answering

August 26, 2025

Wei Zhou이 [arXiv]에 게시한 ‘ST-Raptor: LLM-Powered Semi-Structured Table Question Answering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hierarchical Orthogonal Tree

[논문리뷰] ST-Raptor: LLM-Powered Semi-Structured Table Question Answering

August 26, 2025

Wei Zhou이 [arXiv]에 게시한 ‘ST-Raptor: LLM-Powered Semi-Structured Table Question Answering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Table Layout Understanding

[논문리뷰] ST-Raptor: LLM-Powered Semi-Structured Table Question Answering

August 26, 2025

Wei Zhou이 [arXiv]에 게시한 ‘ST-Raptor: LLM-Powered Semi-Structured Table Question Answering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pipeline Generation

[논문리뷰] ST-Raptor: LLM-Powered Semi-Structured Table Question Answering

August 26, 2025

Wei Zhou이 [arXiv]에 게시한 ‘ST-Raptor: LLM-Powered Semi-Structured Table Question Answering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Verification Mechanism

[논문리뷰] ST-Raptor: LLM-Powered Semi-Structured Table Question Answering

August 26, 2025

Wei Zhou이 [arXiv]에 게시한 ‘ST-Raptor: LLM-Powered Semi-Structured Table Question Answering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visually-Guided Image Editing

[논문리뷰] SpotEdit: Evaluating Visually-Guided Image Editing Methods

August 26, 2025

Ersin Yumer이 [arXiv]에 게시한 ‘SpotEdit: Evaluating Visually-Guided Image Editing Methods’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Idiom Interpretation

[논문리뷰] T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation

August 26, 2025

Xihui Liu이 [arXiv]에 게시한 ‘T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Textual Image Design

[논문리뷰] T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation

August 26, 2025

Xihui Liu이 [arXiv]에 게시한 ‘T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Entity Reasoning

[논문리뷰] T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation

August 26, 2025

Xihui Liu이 [arXiv]에 게시한 ‘T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal LLM Evaluation

[논문리뷰] T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation

August 26, 2025

Xihui Liu이 [arXiv]에 게시한 ‘T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Speech Language Modeling

[논문리뷰] TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling

August 26, 2025

Jiaqi Li이 [arXiv]에 게시한 ‘TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Low Bitrate Codec

[논문리뷰] TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling

August 26, 2025

Jiaqi Li이 [arXiv]에 게시한 ‘TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

End-to-End Training

[논문리뷰] TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling

August 26, 2025

Jiaqi Li이 [arXiv]에 게시한 ‘TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Binary Spherical Quantization

[논문리뷰] TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling

August 26, 2025

Jiaqi Li이 [arXiv]에 게시한 ‘TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Unsolved Questions

[논문리뷰] UQ: Assessing Language Models on Unsolved Questions

August 26, 2025

Wei Liu이 [arXiv]에 게시한 ‘UQ: Assessing Language Models on Unsolved Questions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AI Benchmark

[논문리뷰] UQ: Assessing Language Models on Unsolved Questions

August 26, 2025

Wei Liu이 [arXiv]에 게시한 ‘UQ: Assessing Language Models on Unsolved Questions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Oracle-Free Validation

[논문리뷰] UQ: Assessing Language Models on Unsolved Questions

August 26, 2025

Wei Liu이 [arXiv]에 게시한 ‘UQ: Assessing Language Models on Unsolved Questions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Generator-Validator Gap

[논문리뷰] UQ: Assessing Language Models on Unsolved Questions

August 26, 2025

Wei Liu이 [arXiv]에 게시한 ‘UQ: Assessing Language Models on Unsolved Questions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Community Evaluation

[논문리뷰] UQ: Assessing Language Models on Unsolved Questions

August 26, 2025

Wei Liu이 [arXiv]에 게시한 ‘UQ: Assessing Language Models on Unsolved Questions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Stack Exchange

[논문리뷰] UQ: Assessing Language Models on Unsolved Questions

August 26, 2025

Wei Liu이 [arXiv]에 게시한 ‘UQ: Assessing Language Models on Unsolved Questions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Chain of Thought

[논문리뷰] Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation

August 26, 2025

Haoxiang Shi이 [arXiv]에 게시한 ‘Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Stage-Aware Rewards

[논문리뷰] Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation

August 26, 2025

Haoxiang Shi이 [arXiv]에 게시한 ‘Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Universal Model

[논문리뷰] Autoregressive Universal Video Segmentation Model

August 27, 2025

Albert Gu이 [arXiv]에 게시한 ‘Autoregressive Universal Video Segmentation Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mamba

[논문리뷰] Autoregressive Universal Video Segmentation Model

August 27, 2025

Albert Gu이 [arXiv]에 게시한 ‘Autoregressive Universal Video Segmentation Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Streaming Video

[논문리뷰] Autoregressive Universal Video Segmentation Model

August 27, 2025

Albert Gu이 [arXiv]에 게시한 ‘Autoregressive Universal Video Segmentation Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Condensed Matter Physics

[논문리뷰] CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics

August 27, 2025

Dongchen Huang이 [arXiv]에 게시한 ‘CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Evaluation Metric

[논문리뷰] CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics

August 27, 2025

Dongchen Huang이 [arXiv]에 게시한 ‘CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Expression Edit Distance

[논문리뷰] CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics

August 27, 2025

Dongchen Huang이 [arXiv]에 게시한 ‘CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Problem Solving

[논문리뷰] CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics

August 27, 2025

Dongchen Huang이 [arXiv]에 게시한 ‘CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

High-Resolution Generation

[논문리뷰] CineScale: Free Lunch in High-Resolution Cinematic Visual Generation

August 27, 2025

Ziwei Liu이 [arXiv]에 게시한 ‘CineScale: Free Lunch in High-Resolution Cinematic Visual Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

UNet Architecture

[논문리뷰] CineScale: Free Lunch in High-Resolution Cinematic Visual Generation

August 27, 2025

Ziwei Liu이 [arXiv]에 게시한 ‘CineScale: Free Lunch in High-Resolution Cinematic Visual Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

DiT Architecture

[논문리뷰] CineScale: Free Lunch in High-Resolution Cinematic Visual Generation

August 27, 2025

Ziwei Liu이 [arXiv]에 게시한 ‘CineScale: Free Lunch in High-Resolution Cinematic Visual Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scale Fusion

[논문리뷰] CineScale: Free Lunch in High-Resolution Cinematic Visual Generation

August 27, 2025

Ziwei Liu이 [arXiv]에 게시한 ‘CineScale: Free Lunch in High-Resolution Cinematic Visual Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LoRA Fine-tuning

[논문리뷰] CineScale: Free Lunch in High-Resolution Cinematic Visual Generation

August 27, 2025

Ziwei Liu이 [arXiv]에 게시한 ‘CineScale: Free Lunch in High-Resolution Cinematic Visual Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Legal AI

[논문리뷰] ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation

August 27, 2025

Kun Kuang이 [arXiv]에 게시한 ‘ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Claim Generation

[논문리뷰] ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation

August 27, 2025

Kun Kuang이 [arXiv]에 게시한 ‘ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Chinese Legal Dataset

[논문리뷰] ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation

August 27, 2025

Kun Kuang이 [arXiv]에 게시한 ‘ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Factuality

[논문리뷰] ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation

August 27, 2025

Kun Kuang이 [arXiv]에 게시한 ‘ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Clarity

[논문리뷰] ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation

August 27, 2025

Kun Kuang이 [arXiv]에 게시한 ‘ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Zero-shot Evaluation

[논문리뷰] ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation

August 27, 2025

Kun Kuang이 [arXiv]에 게시한 ‘ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning Probing

[논문리뷰] Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning

August 27, 2025

Arman Cohan이 [arXiv]에 게시한 ‘Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Component Decoupling

[논문리뷰] FastMesh:Efficient Artistic Mesh Generation via Component Decoupling

August 27, 2025

Xingang Pan이 [arXiv]에 게시한 ‘FastMesh:Efficient Artistic Mesh Generation via Component Decoupling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bidirectional Transformer

[논문리뷰] FastMesh:Efficient Artistic Mesh Generation via Component Decoupling

August 27, 2025

Xingang Pan이 [arXiv]에 게시한 ‘FastMesh:Efficient Artistic Mesh Generation via Component Decoupling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fidelity Enhancement

[논문리뷰] FastMesh:Efficient Artistic Mesh Generation via Component Decoupling

August 27, 2025

Xingang Pan이 [arXiv]에 게시한 ‘FastMesh:Efficient Artistic Mesh Generation via Component Decoupling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Prediction Filtering

[논문리뷰] FastMesh:Efficient Artistic Mesh Generation via Component Decoupling

August 27, 2025

Xingang Pan이 [arXiv]에 게시한 ‘FastMesh:Efficient Artistic Mesh Generation via Component Decoupling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Token Efficiency

[논문리뷰] FastMesh:Efficient Artistic Mesh Generation via Component Decoupling

August 27, 2025

Xingang Pan이 [arXiv]에 게시한 ‘FastMesh:Efficient Artistic Mesh Generation via Component Decoupling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Artistic Meshes

[논문리뷰] FastMesh:Efficient Artistic Mesh Generation via Component Decoupling

August 27, 2025

Xingang Pan이 [arXiv]에 게시한 ‘FastMesh:Efficient Artistic Mesh Generation via Component Decoupling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Question Answering (VQA)

[논문리뷰] MovieCORE: COgnitive REasoning in Movies

August 27, 2025

Hung-Ting Su이 [arXiv]에 게시한 ‘MovieCORE: COgnitive REasoning in Movies’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

System-2 Thinking

[논문리뷰] MovieCORE: COgnitive REasoning in Movies

August 27, 2025

Hung-Ting Su이 [arXiv]에 게시한 ‘MovieCORE: COgnitive REasoning in Movies’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-agent LLMs

[논문리뷰] MovieCORE: COgnitive REasoning in Movies

August 27, 2025

Hung-Ting Su이 [arXiv]에 게시한 ‘MovieCORE: COgnitive REasoning in Movies’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Movie Understanding

[논문리뷰] MovieCORE: COgnitive REasoning in Movies

August 27, 2025

Hung-Ting Su이 [arXiv]에 게시한 ‘MovieCORE: COgnitive REasoning in Movies’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cinematic Content

[논문리뷰] MovieCORE: COgnitive REasoning in Movies

August 27, 2025

Hung-Ting Su이 [arXiv]에 게시한 ‘MovieCORE: COgnitive REasoning in Movies’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agentic Enhancement

[논문리뷰] MovieCORE: COgnitive REasoning in Movies

August 27, 2025

Hung-Ting Su이 [arXiv]에 게시한 ‘MovieCORE: COgnitive REasoning in Movies’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Inpainting

[논문리뷰] ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models

August 27, 2025

Beiqi Chen이 [arXiv]에 게시한 ‘ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-view Consistency

[논문리뷰] ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models

August 27, 2025

Beiqi Chen이 [arXiv]에 게시한 ‘ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Object Completion

[논문리뷰] ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models

August 27, 2025

Beiqi Chen이 [arXiv]에 게시한 ‘ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Avatar Generation

[논문리뷰] OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation

August 27, 2025

Jiaqi Yang이 [arXiv]에 게시한 ‘OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cognitive Simulation

[논문리뷰] OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation

August 27, 2025

Jiaqi Yang이 [arXiv]에 게시한 ‘OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Fusion

[논문리뷰] OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation

August 27, 2025

Jiaqi Yang이 [arXiv]에 게시한 ‘OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Contextual Animation

[논문리뷰] OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation

August 27, 2025

Jiaqi Yang이 [arXiv]에 게시한 ‘OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sparsity

[논문리뷰] Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks

August 27, 2025

Daisuke Nohara이 [arXiv]에 게시한 ‘Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Memorization

[논문리뷰] Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks

August 27, 2025

Daisuke Nohara이 [arXiv]에 게시한 ‘Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Top-k Routing

[논문리뷰] Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks

August 27, 2025

Daisuke Nohara이 [arXiv]에 게시한 ‘Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Physics Prediction

[논문리뷰] Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels

August 27, 2025

Dinesh Jayaraman이 [arXiv]에 게시한 ‘Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

CLIP Features

[논문리뷰] Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels

August 27, 2025

Dinesh Jayaraman이 [arXiv]에 게시한 ‘Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Material Point Method

[논문리뷰] Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels

August 27, 2025

Dinesh Jayaraman이 [arXiv]에 게시한 ‘Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

PIXIEVERSE Dataset

[논문리뷰] Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels

August 27, 2025

Dinesh Jayaraman이 [arXiv]에 게시한 ‘Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Contextual Bandits

[논문리뷰] QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting

August 27, 2025

Manuela Veloso이 [arXiv]에 게시한 ‘QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Query Rewriting

[논문리뷰] QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting

August 27, 2025

Manuela Veloso이 [arXiv]에 게시한 ‘QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

No-Regret Learning

[논문리뷰] QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting

August 27, 2025

Manuela Veloso이 [arXiv]에 게시한 ‘QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Academic Survey

[논문리뷰] ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks

August 27, 2025

Kai Jia이 [arXiv]에 게시한 ‘ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Citation Verification

[논문리뷰] ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks

August 27, 2025

Kai Jia이 [arXiv]에 게시한 ‘ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Decontextualization

[논문리뷰] Spacer: Towards Engineered Scientific Inspiration

August 27, 2025

zerojun48이 [arXiv]에 게시한 ‘Spacer: Towards Engineered Scientific Inspiration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Keyword Graph

[논문리뷰] Spacer: Towards Engineered Scientific Inspiration

August 27, 2025

zerojun48이 [arXiv]에 게시한 ‘Spacer: Towards Engineered Scientific Inspiration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scientific Ideation

[논문리뷰] Spacer: Towards Engineered Scientific Inspiration

August 27, 2025

zerojun48이 [arXiv]에 게시한 ‘Spacer: Towards Engineered Scientific Inspiration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Inspiration Engine

[논문리뷰] Spacer: Towards Engineered Scientific Inspiration

August 27, 2025

zerojun48이 [arXiv]에 게시한 ‘Spacer: Towards Engineered Scientific Inspiration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Controllable Reasoning

[논문리뷰] ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models

August 27, 2025

Jiangjie Chen이 [arXiv]에 게시한 ‘ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning Compression

[논문리뷰] ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models

August 27, 2025

Jiangjie Chen이 [arXiv]에 게시한 ‘ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Budget-Aware Training

[논문리뷰] ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models

August 27, 2025

Jiangjie Chen이 [arXiv]에 게시한 ‘ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Execution Environments

[논문리뷰] Training Language Model Agents to Find Vulnerabilities with CTF-Dojo

August 27, 2025

Zijian Wang이 [arXiv]에 게시한 ‘Training Language Model Agents to Find Vulnerabilities with CTF-Dojo’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Automated Training

[논문리뷰] Training Language Model Agents to Find Vulnerabilities with CTF-Dojo

August 27, 2025

Zijian Wang이 [arXiv]에 게시한 ‘Training Language Model Agents to Find Vulnerabilities with CTF-Dojo’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Verifiable Feedback

[논문리뷰] Training Language Model Agents to Find Vulnerabilities with CTF-Dojo

August 27, 2025

Zijian Wang이 [arXiv]에 게시한 ‘Training Language Model Agents to Find Vulnerabilities with CTF-Dojo’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Segment-level Decoding

[논문리뷰] TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling

August 27, 2025

Zhoufutu Wen이 [arXiv]에 게시한 ‘TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling’ 논문에 대한 ...

Back to Top ↑

Memory Networks

[논문리뷰] UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning

August 27, 2025

Ran Guo이 [arXiv]에 게시한 ‘UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long-Context Learning

[논문리뷰] UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning

August 27, 2025

Ran Guo이 [arXiv]에 게시한 ‘UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sparse Models

[논문리뷰] UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning

August 27, 2025

Ran Guo이 [arXiv]에 게시한 ‘UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Network Community Structure

[논문리뷰] Unraveling the cognitive patterns of Large Language Models through module communities

August 27, 2025

Jianxi Gao이 [arXiv]에 게시한 ‘Unraveling the cognitive patterns of Large Language Models through module communities’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cognitive Skills

[논문리뷰] Unraveling the cognitive patterns of Large Language Models through module communities

August 27, 2025

Jianxi Gao이 [arXiv]에 게시한 ‘Unraveling the cognitive patterns of Large Language Models through module communities’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AI Interpretability

[논문리뷰] Unraveling the cognitive patterns of Large Language Models through module communities

August 27, 2025

Jianxi Gao이 [arXiv]에 게시한 ‘Unraveling the cognitive patterns of Large Language Models through module communities’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Module Communities

[논문리뷰] Unraveling the cognitive patterns of Large Language Models through module communities

August 27, 2025

Jianxi Gao이 [arXiv]에 게시한 ‘Unraveling the cognitive patterns of Large Language Models through module communities’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Neural Plasticity

[논문리뷰] Unraveling the cognitive patterns of Large Language Models through module communities

August 27, 2025

Jianxi Gao이 [arXiv]에 게시한 ‘Unraveling the cognitive patterns of Large Language Models through module communities’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long-form Audio

[논문리뷰] VibeVoice Technical Report

August 27, 2025

Yaoyao Chang이 [arXiv]에 게시한 ‘VibeVoice Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-speaker

[논문리뷰] VibeVoice Technical Report

August 27, 2025

Yaoyao Chang이 [arXiv]에 게시한 ‘VibeVoice Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Next-token Diffusion

[논문리뷰] VibeVoice Technical Report

August 27, 2025

Yaoyao Chang이 [arXiv]에 게시한 ‘VibeVoice Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Audio Compression

[논문리뷰] VibeVoice Technical Report

August 27, 2025

Yaoyao Chang이 [arXiv]에 게시한 ‘VibeVoice Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Inversion

[논문리뷰] VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space

August 27, 2025

Rui Chen이 [arXiv]에 게시한 ‘VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Contextual Feature Replacement

[논문리뷰] VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space

August 27, 2025

Rui Chen이 [arXiv]에 게시한 ‘VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Edit3D-Bench

[논문리뷰] VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space

August 27, 2025

Rui Chen이 [arXiv]에 게시한 ‘VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Audio-Driven Video Generation

[논문리뷰] Wan-S2V: Audio-Driven Cinematic Video Generation

August 27, 2025

Chaonan Ji이 [arXiv]에 게시한 ‘Wan-S2V: Audio-Driven Cinematic Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cinematic Video

[논문리뷰] Wan-S2V: Audio-Driven Cinematic Video Generation

August 27, 2025

Chaonan Ji이 [arXiv]에 게시한 ‘Wan-S2V: Audio-Driven Cinematic Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long Video Consistency

[논문리뷰] Wan-S2V: Audio-Driven Cinematic Video Generation

August 27, 2025

Chaonan Ji이 [arXiv]에 게시한 ‘Wan-S2V: Audio-Driven Cinematic Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human Animation

[논문리뷰] Wan-S2V: Audio-Driven Cinematic Video Generation

August 27, 2025

Chaonan Ji이 [arXiv]에 게시한 ‘Wan-S2V: Audio-Driven Cinematic Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Control

[논문리뷰] Wan-S2V: Audio-Driven Cinematic Video Generation

August 27, 2025

Chaonan Ji이 [arXiv]에 게시한 ‘Wan-S2V: Audio-Driven Cinematic Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long-Form Audio Generation

[논문리뷰] AudioStory: Generating Long-Form Narrative Audio with Large Language Models

August 28, 2025

Yixiao Ge이 [arXiv]에 게시한 ‘AudioStory: Generating Long-Form Narrative Audio with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Narrative Reasoning

[논문리뷰] AudioStory: Generating Long-Form Narrative Audio with Large Language Models

August 28, 2025

Yixiao Ge이 [arXiv]에 게시한 ‘AudioStory: Generating Long-Form Narrative Audio with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Logit Lens

[논문리뷰] Beyond Transcription: Mechanistic Interpretability in ASR

August 28, 2025

Aviv Shamsian이 [arXiv]에 게시한 ‘Beyond Transcription: Mechanistic Interpretability in ASR’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Linear Probing

[논문리뷰] Beyond Transcription: Mechanistic Interpretability in ASR

August 28, 2025

Aviv Shamsian이 [arXiv]에 게시한 ‘Beyond Transcription: Mechanistic Interpretability in ASR’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Activation Patching

[논문리뷰] Beyond Transcription: Mechanistic Interpretability in ASR

August 28, 2025

Aviv Shamsian이 [arXiv]에 게시한 ‘Beyond Transcription: Mechanistic Interpretability in ASR’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Repetitions

[논문리뷰] Beyond Transcription: Mechanistic Interpretability in ASR

August 28, 2025

Aviv Shamsian이 [arXiv]에 게시한 ‘Beyond Transcription: Mechanistic Interpretability in ASR’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Planner-Executor Architecture

[논문리뷰] CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

August 28, 2025

Jianze Liang이 [arXiv]에 게시한 ‘CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning’ 논문에 대한 ...

Back to Top ↑

Decoupled Training

[논문리뷰] CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

August 28, 2025

Jianze Liang이 [arXiv]에 게시한 ‘CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning’ 논문에 대한 ...

Back to Top ↑

Large Vision-Language Models

[논문리뷰] CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

August 28, 2025

Jianze Liang이 [arXiv]에 게시한 ‘CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning’ 논문에 대한 ...

Back to Top ↑

Specialization

[논문리뷰] CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

August 28, 2025

Jianze Liang이 [arXiv]에 게시한 ‘CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning’ 논문에 대한 ...

Back to Top ↑

Generative Research Synthesis

[논문리뷰] DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis

August 28, 2025

Ion Stoica이 [arXiv]에 게시한 ‘DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM-as-a-judge

[논문리뷰] DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis

August 28, 2025

Ion Stoica이 [arXiv]에 게시한 ‘DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Related Work Generation

[논문리뷰] DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis

August 28, 2025

Ion Stoica이 [arXiv]에 게시한 ‘DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Verifiability

[논문리뷰] DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis

August 28, 2025

Ion Stoica이 [arXiv]에 게시한 ‘DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

DLM Acceleration

[논문리뷰] Diffusion Language Models Know the Answer Before Decoding

August 28, 2025

Shilin Yan이 [arXiv]에 게시한 ‘Diffusion Language Models Know the Answer Before Decoding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Early Answer Convergence

[논문리뷰] Diffusion Language Models Know the Answer Before Decoding

August 28, 2025

Shilin Yan이 [arXiv]에 게시한 ‘Diffusion Language Models Know the Answer Before Decoding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Early Commit Decoding

[논문리뷰] Diffusion Language Models Know the Answer Before Decoding

August 28, 2025

Shilin Yan이 [arXiv]에 게시한 ‘Diffusion Language Models Know the Answer Before Decoding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Confidence Gap

[논문리뷰] Diffusion Language Models Know the Answer Before Decoding

August 28, 2025

Shilin Yan이 [arXiv]에 게시한 ‘Diffusion Language Models Know the Answer Before Decoding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Inference Speedup

[논문리뷰] Diffusion Language Models Know the Answer Before Decoding

August 28, 2025

Shilin Yan이 [arXiv]에 게시한 ‘Diffusion Language Models Know the Answer Before Decoding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Action Decoding

[논문리뷰] Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies

August 28, 2025

Sitong Mao이 [arXiv]에 게시한 ‘Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Masked Modeling

[논문리뷰] Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies

August 28, 2025

Sitong Mao이 [arXiv]에 게시한 ‘Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adaptive Decoding

[논문리뷰] Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies

August 28, 2025

Sitong Mao이 [arXiv]에 게시한 ‘Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

rPPG

[논문리뷰] Gaze into the Heart: A Multi-View Video Dataset for rPPG and Health Biomarkers Estimation

August 28, 2025

Anton Ivaschenko이 [arXiv]에 게시한 ‘Gaze into the Heart: A Multi-View Video Dataset for rPPG and Health Biomarkers Estimation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-View Video Dataset

[논문리뷰] Gaze into the Heart: A Multi-View Video Dataset for rPPG and Health Biomarkers Estimation

August 28, 2025

Anton Ivaschenko이 [arXiv]에 게시한 ‘Gaze into the Heart: A Multi-View Video Dataset for rPPG and Health Biomarkers Estimation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Health Biomarkers

[논문리뷰] Gaze into the Heart: A Multi-View Video Dataset for rPPG and Health Biomarkers Estimation

August 28, 2025

Anton Ivaschenko이 [arXiv]에 게시한 ‘Gaze into the Heart: A Multi-View Video Dataset for rPPG and Health Biomarkers Estimation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Physiological Monitoring

[논문리뷰] Gaze into the Heart: A Multi-View Video Dataset for rPPG and Health Biomarkers Estimation

August 28, 2025

Anton Ivaschenko이 [arXiv]에 게시한 ‘Gaze into the Heart: A Multi-View Video Dataset for rPPG and Health Biomarkers Estimation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Telemedicine

[논문리뷰] Gaze into the Heart: A Multi-View Video Dataset for rPPG and Health Biomarkers Estimation

August 28, 2025

Anton Ivaschenko이 [arXiv]에 게시한 ‘Gaze into the Heart: A Multi-View Video Dataset for rPPG and Health Biomarkers Estimation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Biosignals

[논문리뷰] Gaze into the Heart: A Multi-View Video Dataset for rPPG and Health Biomarkers Estimation

August 28, 2025

Anton Ivaschenko이 [arXiv]에 게시한 ‘Gaze into the Heart: A Multi-View Video Dataset for rPPG and Health Biomarkers Estimation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Digital Human Synthesis

[논문리뷰] MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation

August 28, 2025

Yan Zhou이 [arXiv]에 게시한 ‘MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-time Video Generation

[논문리뷰] MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation

August 28, 2025

Yan Zhou이 [arXiv]에 게시한 ‘MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Autoregressive LLM

[논문리뷰] MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation

August 28, 2025

Yan Zhou이 [arXiv]에 게시한 ‘MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Deep Compression Autoencoder

[논문리뷰] MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation

August 28, 2025

Yan Zhou이 [arXiv]에 게시한 ‘MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Exposure Bias Mitigation

[논문리뷰] MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation

August 28, 2025

Yan Zhou이 [arXiv]에 게시한 ‘MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal LLMs (MLLMs)

[논문리뷰] Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents

August 28, 2025

Yue Yao이 [arXiv]에 게시한 ‘Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Smartphone Agents

[논문리뷰] Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents

August 28, 2025

Yue Yao이 [arXiv]에 게시한 ‘Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Privacy Awareness

[논문리뷰] Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents

August 28, 2025

Yue Yao이 [arXiv]에 게시한 ‘Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sensitive Data Detection

[논문리뷰] Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents

August 28, 2025

Yue Yao이 [arXiv]에 게시한 ‘Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Risk Assessment

[논문리뷰] Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents

August 28, 2025

Yue Yao이 [arXiv]에 게시한 ‘Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-Guided Motion Generation

[논문리뷰] MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment

August 28, 2025

An-An Liu이 [arXiv]에 게시한 ‘MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Rectified Flow Matching

[논문리뷰] MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment

August 28, 2025

An-An Liu이 [arXiv]에 게시한 ‘MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-time AI

[논문리뷰] MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment

August 28, 2025

An-An Liu이 [arXiv]에 게시한 ‘MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Language Modeling

[논문리뷰] Predicting the Order of Upcoming Tokens Improves Language Modeling

August 28, 2025

Alham Fikri Aji이 [arXiv]에 게시한 ‘Predicting the Order of Upcoming Tokens Improves Language Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Token Prediction

[논문리뷰] Predicting the Order of Upcoming Tokens Improves Language Modeling

August 28, 2025

Alham Fikri Aji이 [arXiv]에 게시한 ‘Predicting the Order of Upcoming Tokens Improves Language Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Token Order Prediction

[논문리뷰] Predicting the Order of Upcoming Tokens Improves Language Modeling

August 28, 2025

Alham Fikri Aji이 [arXiv]에 게시한 ‘Predicting the Order of Upcoming Tokens Improves Language Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Auxiliary Objective

[논문리뷰] Predicting the Order of Upcoming Tokens Improves Language Modeling

August 28, 2025

Alham Fikri Aji이 [arXiv]에 게시한 ‘Predicting the Order of Upcoming Tokens Improves Language Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Learning-to-Rank

[논문리뷰] Predicting the Order of Upcoming Tokens Improves Language Modeling

August 28, 2025

Alham Fikri Aji이 [arXiv]에 게시한 ‘Predicting the Order of Upcoming Tokens Improves Language Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Rewarding

[논문리뷰] Self-Rewarding Vision-Language Model via Reasoning Decomposition

August 28, 2025

Zhenwen Liang이 [arXiv]에 게시한 ‘Self-Rewarding Vision-Language Model via Reasoning Decomposition’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning Decomposition

[논문리뷰] Self-Rewarding Vision-Language Model via Reasoning Decomposition

August 28, 2025

Zhenwen Liang이 [arXiv]에 게시한 ‘Self-Rewarding Vision-Language Model via Reasoning Decomposition’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Language Reasoning

[논문리뷰] Self-Rewarding Vision-Language Model via Reasoning Decomposition

August 28, 2025

Zhenwen Liang이 [arXiv]에 게시한 ‘Self-Rewarding Vision-Language Model via Reasoning Decomposition’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Language Shortcuts

[논문리뷰] Self-Rewarding Vision-Language Model via Reasoning Decomposition

August 28, 2025

Zhenwen Liang이 [arXiv]에 게시한 ‘Self-Rewarding Vision-Language Model via Reasoning Decomposition’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Generative Judges

[논문리뷰] StepWiser: Stepwise Generative Judges for Wiser Reasoning

August 28, 2025

Olga Golovneva이 [arXiv]에 게시한 ‘StepWiser: Stepwise Generative Judges for Wiser Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Stepwise Feedback

[논문리뷰] StepWiser: Stepwise Generative Judges for Wiser Reasoning

August 28, 2025

Olga Golovneva이 [arXiv]에 게시한 ‘StepWiser: Stepwise Generative Judges for Wiser Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Meta-Reasoning

[논문리뷰] StepWiser: Stepwise Generative Judges for Wiser Reasoning

August 28, 2025

Olga Golovneva이 [arXiv]에 게시한 ‘StepWiser: Stepwise Generative Judges for Wiser Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Autoscaling

[논문리뷰] Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference

August 28, 2025

Chunlei Han이 [arXiv]에 게시한 ‘Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Disaggregated Architecture

[논문리뷰] Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference

August 28, 2025

Chunlei Han이 [arXiv]에 게시한 ‘Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Heterogeneous Hardware

[논문리뷰] Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference

August 28, 2025

Chunlei Han이 [arXiv]에 게시한 ‘Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Topology-aware Scheduling

[논문리뷰] Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference

August 28, 2025

Chunlei Han이 [arXiv]에 게시한 ‘Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GPU Utilization

[논문리뷰] Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference

August 28, 2025

Chunlei Han이 [arXiv]에 게시한 ‘Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Distributed Systems

[논문리뷰] AWorld: Orchestrating the Training Recipe for Agentic AI

August 29, 2025

Qintong Wu이 [arXiv]에 게시한 ‘AWorld: Orchestrating the Training Recipe for Agentic AI’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Experience Generation

[논문리뷰] AWorld: Orchestrating the Training Recipe for Agentic AI

August 29, 2025

Qintong Wu이 [arXiv]에 게시한 ‘AWorld: Orchestrating the Training Recipe for Agentic AI’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AWORLD Framework

[논문리뷰] AWorld: Orchestrating the Training Recipe for Agentic AI

August 29, 2025

Qintong Wu이 [arXiv]에 게시한 ‘AWorld: Orchestrating the Training Recipe for Agentic AI’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vision-Language-Action Model

[논문리뷰] CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification

August 29, 2025

Liqiang Nie이 [arXiv]에 게시한 ‘CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Instruction-Driven Routing

[논문리뷰] CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification

August 29, 2025

Liqiang Nie이 [arXiv]에 게시한 ‘CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cognition-Aligned AI

[논문리뷰] CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification

August 29, 2025

Liqiang Nie이 [arXiv]에 게시한 ‘CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Triplane Representation

[논문리뷰] Collaborative Multi-Modal Coding for High-Quality 3D Generation

August 29, 2025

Ziwei Liu이 [arXiv]에 게시한 ‘Collaborative Multi-Modal Coding for High-Quality 3D Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Collaborative Coding

[논문리뷰] Collaborative Multi-Modal Coding for High-Quality 3D Generation

August 29, 2025

Ziwei Liu이 [arXiv]에 게시한 ‘Collaborative Multi-Modal Coding for High-Quality 3D Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-modal Conditioning

[논문리뷰] Dress&Dance: Dress up and Dance as You Like It - Technical Preview

August 29, 2025

Yu-Xiong Wang이 [arXiv]에 게시한 ‘Dress&Dance: Dress up and Dance as You Like It - Technical Preview’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Garment Transfer

[논문리뷰] Dress&Dance: Dress up and Dance as You Like It - Technical Preview

August 29, 2025

Yu-Xiong Wang이 [arXiv]에 게시한 ‘Dress&Dance: Dress up and Dance as You Like It - Technical Preview’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pose Animation

[논문리뷰] Dress&Dance: Dress up and Dance as You Like It - Technical Preview

August 29, 2025

Yu-Xiong Wang이 [arXiv]에 게시한 ‘Dress&Dance: Dress up and Dance as You Like It - Technical Preview’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fashion Tech

[논문리뷰] Dress&Dance: Dress up and Dance as You Like It - Technical Preview

August 29, 2025

Yu-Xiong Wang이 [arXiv]에 게시한 ‘Dress&Dance: Dress up and Dance as You Like It - Technical Preview’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

CondNet

[논문리뷰] Dress&Dance: Dress up and Dance as You Like It - Technical Preview

August 29, 2025

Yu-Xiong Wang이 [arXiv]에 게시한 ‘Dress&Dance: Dress up and Dance as You Like It - Technical Preview’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Deepfake Detection

[논문리뷰] FakeParts: a New Family of AI-Generated DeepFakes

August 29, 2025

Xi Wang이 [arXiv]에 게시한 ‘FakeParts: a New Family of AI-Generated DeepFakes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Partial Deepfakes

[논문리뷰] FakeParts: a New Family of AI-Generated DeepFakes

August 29, 2025

Xi Wang이 [arXiv]에 게시한 ‘FakeParts: a New Family of AI-Generated DeepFakes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AI-Generated Video

[논문리뷰] FakeParts: a New Family of AI-Generated DeepFakes

August 29, 2025

Xi Wang이 [arXiv]에 게시한 ‘FakeParts: a New Family of AI-Generated DeepFakes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Forensics

[논문리뷰] FakeParts: a New Family of AI-Generated DeepFakes

August 29, 2025

Xi Wang이 [arXiv]에 게시한 ‘FakeParts: a New Family of AI-Generated DeepFakes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Manipulation Detection

[논문리뷰] FakeParts: a New Family of AI-Generated DeepFakes

August 29, 2025

Xi Wang이 [arXiv]에 게시한 ‘FakeParts: a New Family of AI-Generated DeepFakes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-Domain Orchestration

[논문리뷰] MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

August 29, 2025

Shashank Biju이 [arXiv]에 게시한 ‘MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fuzzy Instructions

[논문리뷰] MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

August 29, 2025

Shashank Biju이 [arXiv]에 게시한 ‘MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Step Tasks

[논문리뷰] MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

August 29, 2025

Shashank Biju이 [arXiv]에 게시한 ‘MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-World Scenarios

[논문리뷰] MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

August 29, 2025

Shashank Biju이 [arXiv]에 게시한 ‘MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long Video Generation

[논문리뷰] Mixture of Contexts for Long Video Generation

August 29, 2025

Junfei Xiao이 [arXiv]에 게시한 ‘Mixture of Contexts for Long Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Context Routing

[논문리뷰] Mixture of Contexts for Long Video Generation

August 29, 2025

Junfei Xiao이 [arXiv]에 게시한 ‘Mixture of Contexts for Long Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Point Tracking

[논문리뷰] Multi-View 3D Point Tracking

August 29, 2025

Irem Demir이 [arXiv]에 게시한 ‘Multi-View 3D Point Tracking’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-View

[논문리뷰] Multi-View 3D Point Tracking

August 29, 2025

Irem Demir이 [arXiv]에 게시한 ‘Multi-View 3D Point Tracking’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

kNN Correlation

[논문리뷰] Multi-View 3D Point Tracking

August 29, 2025

Irem Demir이 [arXiv]에 게시한 ‘Multi-View 3D Point Tracking’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Occlusion Handling

[논문리뷰] Multi-View 3D Point Tracking

August 29, 2025

Irem Demir이 [arXiv]에 게시한 ‘Multi-View 3D Point Tracking’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Feature Fusion

[논문리뷰] Multi-View 3D Point Tracking

August 29, 2025

Irem Demir이 [arXiv]에 게시한 ‘Multi-View 3D Point Tracking’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human-Computer Interaction (HCI)

[논문리뷰] OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models

August 29, 2025

Alex Endert이 [arXiv]에 게시한 ‘OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Goal Tracking

[논문리뷰] OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models

August 29, 2025

Alex Endert이 [arXiv]에 게시한 ‘OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visualization

[논문리뷰] OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models

August 29, 2025

Alex Endert이 [arXiv]에 게시한 ‘OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Turn Dialogue

[논문리뷰] OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models

August 29, 2025

Alex Endert이 [arXiv]에 게시한 ‘OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

User Interface Design

[논문리뷰] OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models

August 29, 2025

Alex Endert이 [arXiv]에 게시한 ‘OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sensemaking

[논문리뷰] OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models

August 29, 2025

Alex Endert이 [arXiv]에 게시한 ‘OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mask-Guided Editing

[논문리뷰] OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning

August 29, 2025

Yitong Wang이 [arXiv]에 게시한 ‘OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human Preference Learning

[논문리뷰] OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning

August 29, 2025

Yitong Wang이 [arXiv]에 게시한 ‘OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Persuasion Dynamics

[논문리뷰] Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD

August 29, 2025

Roy Ka-Wei Lee이 [arXiv]에 게시한 ‘Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gullibility

[논문리뷰] Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD

August 29, 2025

Roy Ka-Wei Lee이 [arXiv]에 게시한 ‘Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Receptiveness

[논문리뷰] Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD

August 29, 2025

Roy Ka-Wei Lee이 [arXiv]에 게시한 ‘Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pairwise Preference

[논문리뷰] Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

August 29, 2025

Jiazi Bu이 [arXiv]에 게시한 ‘Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Stable Optimization

[논문리뷰] Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

August 29, 2025

Jiazi Bu이 [arXiv]에 게시한 ‘Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

UniGenBench

[논문리뷰] Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

August 29, 2025

Jiazi Bu이 [arXiv]에 게시한 ‘Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

In-Tool Learning

[논문리뷰] Provable Benefits of In-Tool Learning for Large Language Models

August 29, 2025

Vivien Cabannes이 [arXiv]에 게시한 ‘Provable Benefits of In-Tool Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

In-Weight Learning

[논문리뷰] Provable Benefits of In-Tool Learning for Large Language Models

August 29, 2025

Vivien Cabannes이 [arXiv]에 게시한 ‘Provable Benefits of In-Tool Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Factual Recall

[논문리뷰] Provable Benefits of In-Tool Learning for Large Language Models

August 29, 2025

Vivien Cabannes이 [arXiv]에 게시한 ‘Provable Benefits of In-Tool Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Object Removal

[논문리뷰] ROSE: Remove Objects with Side Effects in Videos

August 29, 2025

Hantang Liu이 [arXiv]에 게시한 ‘ROSE: Remove Objects with Side Effects in Videos’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Side Effects

[논문리뷰] ROSE: Remove Objects with Side Effects in Videos

August 29, 2025

Hantang Liu이 [arXiv]에 게시한 ‘ROSE: Remove Objects with Side Effects in Videos’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Rendering

[논문리뷰] ROSE: Remove Objects with Side Effects in Videos

August 29, 2025

Hantang Liu이 [arXiv]에 게시한 ‘ROSE: Remove Objects with Side Effects in Videos’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Inpainting

[논문리뷰] ROSE: Remove Objects with Side Effects in Videos

August 29, 2025

Hantang Liu이 [arXiv]에 게시한 ‘ROSE: Remove Objects with Side Effects in Videos’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Difference Mask

[논문리뷰] ROSE: Remove Objects with Side Effects in Videos

August 29, 2025

Hantang Liu이 [arXiv]에 게시한 ‘ROSE: Remove Objects with Side Effects in Videos’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Instruction Augmentation

[논문리뷰] TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning

August 29, 2025

Simin Ma이 [arXiv]에 게시한 ‘TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Task-Centric

[논문리뷰] TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning

August 29, 2025

Simin Ma이 [arXiv]에 게시한 ‘TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Task Alignment

[논문리뷰] TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning

August 29, 2025

Simin Ma이 [arXiv]에 게시한 ‘TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Breadth-First Search

[논문리뷰] TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning

August 29, 2025

Simin Ma이 [arXiv]에 게시한 ‘TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Constraint Generation

[논문리뷰] TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning

August 29, 2025

Simin Ma이 [arXiv]에 게시한 ‘TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Alignment Amplification

[논문리뷰] Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection

August 29, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Rank-One Update

[논문리뷰] Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection

August 29, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Weight Steering

[논문리뷰] Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection

August 29, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Jailbreak Robustness

[논문리뷰] Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection

August 29, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fine-tuning-free

[논문리뷰] Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection

August 29, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Safety Injection

[논문리뷰] Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection

August 29, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Style-Driven Generation

[논문리뷰] USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning

August 29, 2025

Jiahe Tian이 [arXiv]에 게시한 ‘USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Subject-Driven Generation

[논문리뷰] USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning

August 29, 2025

Jiahe Tian이 [arXiv]에 게시한 ‘USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Disentangled Representation

[논문리뷰] USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning

August 29, 2025

Jiahe Tian이 [arXiv]에 게시한 ‘USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reward Learning

[논문리뷰] USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning

August 29, 2025

Jiahe Tian이 [arXiv]에 게시한 ‘USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-Task Learning

[논문리뷰] USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning

August 29, 2025

Jiahe Tian이 [arXiv]에 게시한 ‘USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Code Interpreter

[논문리뷰] rStar2-Agent: Agentic Reasoning Technical Report

August 29, 2025

Weijiang Xu이 [arXiv]에 게시한 ‘rStar2-Agent: Agentic Reasoning Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GRPO-RoC

[논문리뷰] rStar2-Agent: Agentic Reasoning Technical Report

August 29, 2025

Weijiang Xu이 [arXiv]에 게시한 ‘rStar2-Agent: Agentic Reasoning Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Training Efficiency

[논문리뷰] rStar2-Agent: Agentic Reasoning Technical Report

August 29, 2025

Weijiang Xu이 [arXiv]에 게시한 ‘rStar2-Agent: Agentic Reasoning Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Reflection

[논문리뷰] rStar2-Agent: Agentic Reasoning Technical Report

August 29, 2025

Weijiang Xu이 [arXiv]에 게시한 ‘rStar2-Agent: Agentic Reasoning Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AI-Generated Code Security

[논문리뷰] A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code

September 1, 2025

Libo Chen이 [arXiv]에 게시한 ‘A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Repository-Level Benchmark

[논문리뷰] A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code

September 1, 2025

Libo Chen이 [arXiv]에 게시한 ‘A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Code Security

[논문리뷰] A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code

September 1, 2025

Libo Chen이 [arXiv]에 게시한 ‘A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Static Analysis

[논문리뷰] A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code

September 1, 2025

Libo Chen이 [arXiv]에 게시한 ‘A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bias Detection

[논문리뷰] AHELM: A Holistic Evaluation of Audio-Language Models

September 1, 2025

Siwei Yang이 [arXiv]에 게시한 ‘AHELM: A Holistic Evaluation of Audio-Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scientific LLMs

[논문리뷰] A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers

September 1, 2025

Jiamin Wu이 [arXiv]에 게시한 ‘A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scientific Data

[논문리뷰] A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers

September 1, 2025

Jiamin Wu이 [arXiv]에 게시한 ‘A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Integration

[논문리뷰] A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers

September 1, 2025

Jiamin Wu이 [arXiv]에 게시한 ‘A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Knowledge Representation

[논문리뷰] A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers

September 1, 2025

Jiamin Wu이 [arXiv]에 게시한 ‘A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Autonomous Discovery

[논문리뷰] A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers

September 1, 2025

Jiamin Wu이 [arXiv]에 게시한 ‘A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Ecosystems

[논문리뷰] A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers

September 1, 2025

Jiamin Wu이 [arXiv]에 게시한 ‘A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Symmetry Detection

[논문리뷰] CLIPSym: Delving into Symmetry Detection with CLIP

September 1, 2025

Raymond A. Yeh이 [arXiv]에 게시한 ‘CLIPSym: Delving into Symmetry Detection with CLIP’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Equivariant Networks

[논문리뷰] CLIPSym: Delving into Symmetry Detection with CLIP

September 1, 2025

Raymond A. Yeh이 [arXiv]에 게시한 ‘CLIPSym: Delving into Symmetry Detection with CLIP’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Geometric Deep Learning

[논문리뷰] CLIPSym: Delving into Symmetry Detection with CLIP

September 1, 2025

Raymond A. Yeh이 [arXiv]에 게시한 ‘CLIPSym: Delving into Symmetry Detection with CLIP’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spatial Consistency

[논문리뷰] Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation

September 1, 2025

Qi Jia이 [arXiv]에 게시한 ‘Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semantic Knowledge

[논문리뷰] Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation

September 1, 2025

Qi Jia이 [arXiv]에 게시한 ‘Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Code Embeddings

[논문리뷰] Efficient Code Embeddings from Code Generation Models

September 1, 2025

Han Xiao이 [arXiv]에 게시한 ‘Efficient Code Embeddings from Code Generation Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Code Generation Models

[논문리뷰] Efficient Code Embeddings from Code Generation Models

September 1, 2025

Han Xiao이 [arXiv]에 게시한 ‘Efficient Code Embeddings from Code Generation Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Autoregressive Backbones

[논문리뷰] Efficient Code Embeddings from Code Generation Models

September 1, 2025

Han Xiao이 [arXiv]에 게시한 ‘Efficient Code Embeddings from Code Generation Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Last-Token Pooling

[논문리뷰] Efficient Code Embeddings from Code Generation Models

September 1, 2025

Han Xiao이 [arXiv]에 게시한 ‘Efficient Code Embeddings from Code Generation Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

MTEB Benchmark

[논문리뷰] Efficient Code Embeddings from Code Generation Models

September 1, 2025

Han Xiao이 [arXiv]에 게시한 ‘Efficient Code Embeddings from Code Generation Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Pretraining

[논문리뷰] EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control

September 1, 2025

Zhaoqing Chen이 [arXiv]에 게시한 ‘EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-world Robotics

[논문리뷰] EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control

September 1, 2025

Zhaoqing Chen이 [arXiv]에 게시한 ‘EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dexterous Manipulation

[논문리뷰] HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation

September 1, 2025

Tianhai Liang이 [arXiv]에 게시한 ‘HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mobile Manipulation

[논문리뷰] HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation

September 1, 2025

Tianhai Liang이 [arXiv]에 게시한 ‘HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human-to-Robot Learning

[논문리뷰] HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation

September 1, 2025

Tianhai Liang이 [arXiv]에 게시한 ‘HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sim2Real

[논문리뷰] HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation

September 1, 2025

Tianhai Liang이 [arXiv]에 게시한 ‘HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Depth Image

[논문리뷰] HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation

September 1, 2025

Tianhai Liang이 [arXiv]에 게시한 ‘HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Localization

[논문리뷰] HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation

September 1, 2025

Tianhai Liang이 [arXiv]에 게시한 ‘HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bimanual Control

[논문리뷰] HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation

September 1, 2025

Tianhai Liang이 [arXiv]에 게시한 ‘HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Physics Formula Discovery

[논문리뷰] Mimicking the Physicist’s Eye:A VLM-centric Approach for Physics Formula Discovery

September 1, 2025

Wenjie Zhou이 [arXiv]에 게시한 ‘Mimicking the Physicist’s Eye:A VLM-centric Approach for Physics Formula Discovery’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Symbolic Regression

[논문리뷰] Mimicking the Physicist’s Eye:A VLM-centric Approach for Physics Formula Discovery

September 1, 2025

Wenjie Zhou이 [arXiv]에 게시한 ‘Mimicking the Physicist’s Eye:A VLM-centric Approach for Physics Formula Discovery’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Causal Chain of Thought

[논문리뷰] Mimicking the Physicist’s Eye:A VLM-centric Approach for Physics Formula Discovery

September 1, 2025

Wenjie Zhou이 [arXiv]에 게시한 ‘Mimicking the Physicist’s Eye:A VLM-centric Approach for Physics Formula Discovery’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

UI Agents

[논문리뷰] Morae: Proactively Pausing UI Agents for User Choices

September 1, 2025

Amy Pavel이 [arXiv]에 게시한 ‘Morae: Proactively Pausing UI Agents for User Choices’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human-Agent Interaction

[논문리뷰] Morae: Proactively Pausing UI Agents for User Choices

September 1, 2025

Amy Pavel이 [arXiv]에 게시한 ‘Morae: Proactively Pausing UI Agents for User Choices’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mixed-Initiative AI

[논문리뷰] Morae: Proactively Pausing UI Agents for User Choices

September 1, 2025

Amy Pavel이 [arXiv]에 게시한 ‘Morae: Proactively Pausing UI Agents for User Choices’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

User Choice

[논문리뷰] Morae: Proactively Pausing UI Agents for User Choices

September 1, 2025

Amy Pavel이 [arXiv]에 게시한 ‘Morae: Proactively Pausing UI Agents for User Choices’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Blind and Low-Vision Users

[논문리뷰] Morae: Proactively Pausing UI Agents for User Choices

September 1, 2025

Amy Pavel이 [arXiv]에 게시한 ‘Morae: Proactively Pausing UI Agents for User Choices’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Auto-Thinking

[논문리뷰] R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning

September 1, 2025

Han Hu이 [arXiv]에 게시한 ‘R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bi-mode Annealing

[논문리뷰] R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning

September 1, 2025

Han Hu이 [arXiv]에 게시한 ‘R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bi-mode Policy Optimization (BPO)

[논문리뷰] R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning

September 1, 2025

Han Hu이 [arXiv]에 게시한 ‘R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

General-Purpose AI

[논문리뷰] R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning

September 1, 2025

Han Hu이 [arXiv]에 게시한 ‘R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Audio-Driven Talking Head Synthesis

[논문리뷰] TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis

September 1, 2025

Pengcheng Chen이 [arXiv]에 게시한 ‘TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Large-Scale Dataset

[논문리뷰] TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis

September 1, 2025

Pengcheng Chen이 [arXiv]에 게시한 ‘TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Algorithmic Fairness

[논문리뷰] TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis

September 1, 2025

Pengcheng Chen이 [arXiv]에 게시한 ‘TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Procedural Knowledge

[논문리뷰] Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models

September 1, 2025

Yifan Lu이 [arXiv]에 게시한 ‘Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Declarative Knowledge

[논문리뷰] Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models

September 1, 2025

Yifan Lu이 [arXiv]에 게시한 ‘Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Strategic Decision-Making

[논문리뷰] Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models

September 1, 2025

Yifan Lu이 [arXiv]에 게시한 ‘Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Language Model Pre-training

[논문리뷰] TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training

September 1, 2025

Jiyao Deng이 [arXiv]에 게시한 ‘TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dynamic Data Mixing

[논문리뷰] TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training

September 1, 2025

Jiyao Deng이 [arXiv]에 게시한 ‘TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Influence

[논문리뷰] TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training

September 1, 2025

Jiyao Deng이 [arXiv]에 게시한 ‘TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Group Influence

[논문리뷰] TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training

September 1, 2025

Jiyao Deng이 [arXiv]에 게시한 ‘TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Regression Model

[논문리뷰] TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training

September 1, 2025

Jiyao Deng이 [arXiv]에 게시한 ‘TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Foundational Model

[논문리뷰] UItron: Foundational GUI Agent with Advanced Perception and Planning

September 1, 2025

Yufeng Zhong이 [arXiv]에 게시한 ‘UItron: Foundational GUI Agent with Advanced Perception and Planning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Planning

[논문리뷰] UItron: Foundational GUI Agent with Advanced Perception and Planning

September 1, 2025

Yufeng Zhong이 [arXiv]에 게시한 ‘UItron: Foundational GUI Agent with Advanced Perception and Planning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Engineering

[논문리뷰] UItron: Foundational GUI Agent with Advanced Perception and Planning

September 1, 2025

Yufeng Zhong이 [arXiv]에 게시한 ‘UItron: Foundational GUI Agent with Advanced Perception and Planning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Chinese App Scenarios

[논문리뷰] UItron: Foundational GUI Agent with Advanced Perception and Planning

September 1, 2025

Yufeng Zhong이 [arXiv]에 게시한 ‘UItron: Foundational GUI Agent with Advanced Perception and Planning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spatial Cognition

[논문리뷰] From reactive to cognitive: brain-inspired spatial intelligence for embodied agents

September 2, 2025

Songming Liu이 [arXiv]에 게시한 ‘From reactive to cognitive: brain-inspired spatial intelligence for embodied agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Embodied Agents

[논문리뷰] From reactive to cognitive: brain-inspired spatial intelligence for embodied agents

September 2, 2025

Songming Liu이 [arXiv]에 게시한 ‘From reactive to cognitive: brain-inspired spatial intelligence for embodied agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cognitive Map

[논문리뷰] From reactive to cognitive: brain-inspired spatial intelligence for embodied agents

September 2, 2025

Songming Liu이 [arXiv]에 게시한 ‘From reactive to cognitive: brain-inspired spatial intelligence for embodied agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spatial Memory

[논문리뷰] From reactive to cognitive: brain-inspired spatial intelligence for embodied agents

September 2, 2025

Songming Liu이 [arXiv]에 게시한 ‘From reactive to cognitive: brain-inspired spatial intelligence for embodied agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Navigation

[논문리뷰] From reactive to cognitive: brain-inspired spatial intelligence for embodied agents

September 2, 2025

Songming Liu이 [arXiv]에 게시한 ‘From reactive to cognitive: brain-inspired spatial intelligence for embodied agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Input Reformulation

[논문리뷰] How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench

September 2, 2025

Jayanth Srinivasa이 [arXiv]에 게시한 ‘How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench’ 논문에 대한 자세한 리뷰입...

Back to Top ↑

τ-bench

[논문리뷰] How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench

September 2, 2025

Jayanth Srinivasa이 [arXiv]에 게시한 ‘How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench’ 논문에 대한 자세한 리뷰입...

Back to Top ↑

Context Engineering

[논문리뷰] How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench

September 2, 2025

Jayanth Srinivasa이 [arXiv]에 게시한 ‘How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench’ 논문에 대한 자세한 리뷰입...

Back to Top ↑

Multi-Agent Framework

[논문리뷰] How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench

September 2, 2025

Jayanth Srinivasa이 [arXiv]에 게시한 ‘How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench’ 논문에 대한 자세한 리뷰입...

Back to Top ↑

Surface Defect Detection

[논문리뷰] No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes

September 2, 2025

Danijel Skočaj이 [arXiv]에 게시한 ‘No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Anomaly Detection

[논문리뷰] No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes

September 2, 2025

Danijel Skočaj이 [arXiv]에 게시한 ‘No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mixed Supervision

[논문리뷰] No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes

September 2, 2025

Danijel Skočaj이 [arXiv]에 게시한 ‘No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Industrial Inspection

[논문리뷰] No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes

September 2, 2025

Danijel Skočaj이 [arXiv]에 게시한 ‘No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Unified Model

[논문리뷰] No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes

September 2, 2025

Danijel Skočaj이 [arXiv]에 게시한 ‘No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Critic-Free RL

[논문리뷰] PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning

September 2, 2025

Yuewei Zhang이 [arXiv]에 게시한 ‘PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agentic Reasoning

[논문리뷰] PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning

September 2, 2025

Yuewei Zhang이 [arXiv]에 게시한 ‘PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Group Sampling

[논문리뷰] PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning

September 2, 2025

Yuewei Zhang이 [arXiv]에 게시한 ‘PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Static Value Estimation

[논문리뷰] PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning

September 2, 2025

Yuewei Zhang이 [arXiv]에 게시한 ‘PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Table-to-Report Generation

[논문리뷰] T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables

September 2, 2025

Yu Zhao이 [arXiv]에 게시한 ‘T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Industrial Applications

[논문리뷰] T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables

September 2, 2025

Yu Zhao이 [arXiv]에 게시한 ‘T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Table Reasoning

[논문리뷰] T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables

September 2, 2025

Yu Zhao이 [arXiv]에 게시한 ‘T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-world Data

[논문리뷰] T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables

September 2, 2025

Yu Zhao이 [arXiv]에 게시한 ‘T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Arabic LLM

[논문리뷰] UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat

September 2, 2025

Omartificial-Intelligence-Space이 [arXiv]에 게시한 ‘UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

UI-level Evaluation

[논문리뷰] UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat

September 2, 2025

Omartificial-Intelligence-Space이 [arXiv]에 게시한 ‘UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

ALLaM 34B

[논문리뷰] UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat

September 2, 2025

Omartificial-Intelligence-Space이 [arXiv]에 게시한 ‘UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

HUMAIN Chat

[논문리뷰] UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat

September 2, 2025

Omartificial-Intelligence-Space이 [arXiv]에 게시한 ‘UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dialectal Arabic

[논문리뷰] UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat

September 2, 2025

Omartificial-Intelligence-Space이 [arXiv]에 게시한 ‘UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM as a Judge

[논문리뷰] UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat

September 2, 2025

Omartificial-Intelligence-Space이 [arXiv]에 게시한 ‘UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Safety Evaluation

[논문리뷰] UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat

September 2, 2025

Omartificial-Intelligence-Space이 [arXiv]에 게시한 ‘UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Constitutional AI

[논문리뷰] AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models

September 3, 2025

Rahul Karthikeyan이 [arXiv]에 게시한 ‘AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Al...

Back to Top ↑

Inference-Time Control

[논문리뷰] AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models

September 3, 2025

Rahul Karthikeyan이 [arXiv]에 게시한 ‘AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Al...

Back to Top ↑

Indian Sociocultural Context

[논문리뷰] AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models

September 3, 2025

Rahul Karthikeyan이 [arXiv]에 게시한 ‘AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Al...

Back to Top ↑

Genetic Algorithms

[논문리뷰] Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation

September 3, 2025

Xiaolei Huang이 [arXiv]에 게시한 ‘Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation’ 논문에 대한 자...

Back to Top ↑

Textual Data Augmentation

[논문리뷰] Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation

September 3, 2025

Xiaolei Huang이 [arXiv]에 게시한 ‘Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation’ 논문에 대한 자...

Back to Top ↑

Active Learning

[논문리뷰] Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation

September 3, 2025

Xiaolei Huang이 [arXiv]에 게시한 ‘Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation’ 논문에 대한 자...

Back to Top ↑

NLP

[논문리뷰] Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation

September 3, 2025

Xiaolei Huang이 [arXiv]에 게시한 ‘Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation’ 논문에 대한 자...

Back to Top ↑

Medical AI

[논문리뷰] Baichuan-M2: Scaling Medical Capability with Large Verifier System

September 3, 2025

Jayok6이 [arXiv]에 게시한 ‘Baichuan-M2: Scaling Medical Capability with Large Verifier System’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Verifier System

[논문리뷰] Baichuan-M2: Scaling Medical Capability with Large Verifier System

September 3, 2025

Jayok6이 [arXiv]에 게시한 ‘Baichuan-M2: Scaling Medical Capability with Large Verifier System’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Patient Simulator

[논문리뷰] Baichuan-M2: Scaling Medical Capability with Large Verifier System

September 3, 2025

Jayok6이 [arXiv]에 게시한 ‘Baichuan-M2: Scaling Medical Capability with Large Verifier System’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Clinical Rubrics

[논문리뷰] Baichuan-M2: Scaling Medical Capability with Large Verifier System

September 3, 2025

Jayok6이 [arXiv]에 게시한 ‘Baichuan-M2: Scaling Medical Capability with Large Verifier System’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Baichuan-M2

[논문리뷰] Baichuan-M2: Scaling Medical Capability with Large Verifier System

September 3, 2025

Jayok6이 [arXiv]에 게시한 ‘Baichuan-M2: Scaling Medical Capability with Large Verifier System’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

HealthBench

[논문리뷰] Baichuan-M2: Scaling Medical Capability with Large Verifier System

September 3, 2025

Jayok6이 [arXiv]에 게시한 ‘Baichuan-M2: Scaling Medical Capability with Large Verifier System’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Optimizers

[논문리뷰] Benchmarking Optimizers for Large Language Model Pretraining

September 3, 2025

mjaggi이 [arXiv]에 게시한 ‘Benchmarking Optimizers for Large Language Model Pretraining’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AdEMAMix

[논문리뷰] Benchmarking Optimizers for Large Language Model Pretraining

September 3, 2025

mjaggi이 [arXiv]에 게시한 ‘Benchmarking Optimizers for Large Language Model Pretraining’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

MARS

[논문리뷰] Benchmarking Optimizers for Large Language Model Pretraining

September 3, 2025

mjaggi이 [arXiv]에 게시한 ‘Benchmarking Optimizers for Large Language Model Pretraining’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Weight Decay

[논문리뷰] Benchmarking Optimizers for Large Language Model Pretraining

September 3, 2025

mjaggi이 [arXiv]에 게시한 ‘Benchmarking Optimizers for Large Language Model Pretraining’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Object Detection

[논문리뷰] C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection

September 3, 2025

Vito Renó이 [arXiv]에 게시한 ‘C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Global Scene Context

[논문리뷰] C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection

September 3, 2025

Vito Renó이 [arXiv]에 게시한 ‘C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Context-Aware Fusion

[논문리뷰] C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection

September 3, 2025

Vito Renó이 [arXiv]에 게시한 ‘C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fine-grained Detection

[논문리뷰] C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection

September 3, 2025

Vito Renó이 [arXiv]에 게시한 ‘C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Automotive Damage Assessment

[논문리뷰] C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection

September 3, 2025

Vito Renó이 [arXiv]에 게시한 ‘C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Generative Denoising

[논문리뷰] C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection

September 3, 2025

Vito Renó이 [arXiv]에 게시한 ‘C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dynamic Clipping

[논문리뷰] DCPO: Dynamic Clipping Policy Optimization

September 3, 2025

Kai Lu이 [arXiv]에 게시한 ‘DCPO: Dynamic Clipping Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Advantage Standardization

[논문리뷰] DCPO: Dynamic Clipping Policy Optimization

September 3, 2025

Kai Lu이 [arXiv]에 게시한 ‘DCPO: Dynamic Clipping Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Noise Inversion

[논문리뷰] Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing

September 3, 2025

Amin Heyrani Nobar이 [arXiv]에 게시한 ‘Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gumbel-max Trick

[논문리뷰] Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing

September 3, 2025

Amin Heyrani Nobar이 [arXiv]에 게시한 ‘Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Location-aware Argmax Inversion

[논문리뷰] Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing

September 3, 2025

Amin Heyrani Nobar이 [arXiv]에 게시한 ‘Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semantic Aggregation

[논문리뷰] ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding

September 3, 2025

Xuanyu Zheng이 [arXiv]에 게시한 ‘ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video MLLM

[논문리뷰] ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding

September 3, 2025

Xuanyu Zheng이 [arXiv]에 게시한 ‘ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

VideoQA

[논문리뷰] ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding

September 3, 2025

Xuanyu Zheng이 [arXiv]에 게시한 ‘ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Deep Learning Optimizers

[논문리뷰] Fantastic Pretraining Optimizers and Where to Find Them

September 3, 2025

Percy Liang이 [arXiv]에 게시한 ‘Fantastic Pretraining Optimizers and Where to Find Them’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pretraining Speedup

[논문리뷰] Fantastic Pretraining Optimizers and Where to Find Them

September 3, 2025

Percy Liang이 [arXiv]에 게시한 ‘Fantastic Pretraining Optimizers and Where to Find Them’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Matrix-based Optimizers

[논문리뷰] Fantastic Pretraining Optimizers and Where to Find Them

September 3, 2025

Percy Liang이 [arXiv]에 게시한 ‘Fantastic Pretraining Optimizers and Where to Find Them’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data-to-Model Ratio

[논문리뷰] Fantastic Pretraining Optimizers and Where to Find Them

September 3, 2025

Percy Liang이 [arXiv]에 게시한 ‘Fantastic Pretraining Optimizers and Where to Find Them’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cacheable Architecture

[논문리뷰] FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models

September 3, 2025

Zhen Wang이 [arXiv]에 게시한 ‘FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Reference

[논문리뷰] FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models

September 3, 2025

Zhen Wang이 [arXiv]에 게시한 ‘FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semi-Attention

[논문리뷰] FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models

September 3, 2025

Zhen Wang이 [arXiv]에 게시한 ‘FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adventure Games

[논문리뷰] FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games

September 3, 2025

Dongmin Park이 [arXiv]에 게시한 ‘FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Full Story Arc

[논문리뷰] FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games

September 3, 2025

Dongmin Park이 [arXiv]에 게시한 ‘FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Observation-Behavior Gap

[논문리뷰] FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games

September 3, 2025

Dongmin Park이 [arXiv]에 게시한 ‘FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Compositing

[논문리뷰] GenCompositor: Generative Video Compositing with Diffusion Transformer

September 3, 2025

Lingen Li이 [arXiv]에 게시한 ‘GenCompositor: Generative Video Compositing with Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Position Embedding

[논문리뷰] GenCompositor: Generative Video Compositing with Diffusion Transformer

September 3, 2025

Lingen Li이 [arXiv]에 게시한 ‘GenCompositor: Generative Video Compositing with Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Masked Token Injection

[논문리뷰] GenCompositor: Generative Video Compositing with Diffusion Transformer

September 3, 2025

Lingen Li이 [arXiv]에 게시한 ‘GenCompositor: Generative Video Compositing with Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Harmonization

[논문리뷰] GenCompositor: Generative Video Compositing with Diffusion Transformer

September 3, 2025

Lingen Li이 [arXiv]에 게시한 ‘GenCompositor: Generative Video Compositing with Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-Entropy Loss

[논문리뷰] Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR

September 3, 2025

Lu Wang이 [arXiv]에 게시한 ‘Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Large Vision and Language Models (LVLMs)

[논문리뷰] Improving Large Vision and Language Models by Learning from a Panel of Peers

September 3, 2025

Simon Jenni이 [arXiv]에 게시한 ‘Improving Large Vision and Language Models by Learning from a Panel of Peers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Peer Learning

[논문리뷰] Improving Large Vision and Language Models by Learning from a Panel of Peers

September 3, 2025

Simon Jenni이 [arXiv]에 게시한 ‘Improving Large Vision and Language Models by Learning from a Panel of Peers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Diversity Optimization

[논문리뷰] Jointly Reinforcing Diversity and Quality in Language Model Generations

September 3, 2025

Tianlu이 [arXiv]에 게시한 ‘Jointly Reinforcing Diversity and Quality in Language Model Generations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Quality Enhancement

[논문리뷰] Jointly Reinforcing Diversity and Quality in Language Model Generations

September 3, 2025

Tianlu이 [arXiv]에 게시한 ‘Jointly Reinforcing Diversity and Quality in Language Model Generations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semantic Clustering

[논문리뷰] Jointly Reinforcing Diversity and Quality in Language Model Generations

September 3, 2025

Tianlu이 [arXiv]에 게시한 ‘Jointly Reinforcing Diversity and Quality in Language Model Generations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Slow-Fast Encoding

[논문리뷰] Kwai Keye-VL 1.5 Technical Report

September 3, 2025

SXxtyz이 [arXiv]에 게시한 ‘Kwai Keye-VL 1.5 Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human Alignment

[논문리뷰] Kwai Keye-VL 1.5 Technical Report

September 3, 2025

SXxtyz이 [arXiv]에 게시한 ‘Kwai Keye-VL 1.5 Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Native-Resolution Vision Encoder

[논문리뷰] Kwai Keye-VL 1.5 Technical Report

September 3, 2025

SXxtyz이 [arXiv]에 게시한 ‘Kwai Keye-VL 1.5 Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Critic Models

[논문리뷰] LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

September 3, 2025

Jianwei Yang이 [arXiv]에 게시한 ‘LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Policy Models

[논문리뷰] LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

September 3, 2025

Jianwei Yang이 [arXiv]에 게시한 ‘LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Criticism

[논문리뷰] LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

September 3, 2025

Jianwei Yang이 [arXiv]에 게시한 ‘LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Medical Image Retrieval

[논문리뷰] M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision

September 3, 2025

Yan-Jie Zhou이 [arXiv]에 게시한 ‘M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Zero-shot

[논문리뷰] M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision

September 3, 2025

Yan-Jie Zhou이 [arXiv]에 게시한 ‘M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

MAE

[논문리뷰] M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision

September 3, 2025

Yan-Jie Zhou이 [arXiv]에 게시한 ‘M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

SimDINO

[논문리뷰] M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision

September 3, 2025

Yan-Jie Zhou이 [arXiv]에 게시한 ‘M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vision Foundation Models

[논문리뷰] MedDINOv3: How to adapt vision foundation models for medical image segmentation?

September 3, 2025

Xiaofeng Yang이 [arXiv]에 게시한 ‘MedDINOv3: How to adapt vision foundation models for medical image segmentation?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vision Transformers (ViT)

[논문리뷰] MedDINOv3: How to adapt vision foundation models for medical image segmentation?

September 3, 2025

Xiaofeng Yang이 [arXiv]에 게시한 ‘MedDINOv3: How to adapt vision foundation models for medical image segmentation?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

CT Imaging

[논문리뷰] MedDINOv3: How to adapt vision foundation models for medical image segmentation?

September 3, 2025

Xiaofeng Yang이 [arXiv]에 게시한 ‘MedDINOv3: How to adapt vision foundation models for medical image segmentation?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Low-Bit Quantization

[논문리뷰] Metis: Training Large Language Models with Advanced Low-Bit Quantization

September 3, 2025

Hengjie Cao이 [arXiv]에 게시한 ‘Metis: Training Large Language Models with Advanced Low-Bit Quantization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spectral Decomposition

[논문리뷰] Metis: Training Large Language Models with Advanced Low-Bit Quantization

September 3, 2025

Hengjie Cao이 [arXiv]에 게시한 ‘Metis: Training Large Language Models with Advanced Low-Bit Quantization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Anisotropy

[논문리뷰] Metis: Training Large Language Models with Advanced Low-Bit Quantization

September 3, 2025

Hengjie Cao이 [arXiv]에 게시한 ‘Metis: Training Large Language Models with Advanced Low-Bit Quantization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adaptive Learning Rate

[논문리뷰] Metis: Training Large Language Models with Advanced Low-Bit Quantization

September 3, 2025

Hengjie Cao이 [arXiv]에 게시한 ‘Metis: Training Large Language Models with Advanced Low-Bit Quantization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

FP4 Training

[논문리뷰] Metis: Training Large Language Models with Advanced Low-Bit Quantization

September 3, 2025

Hengjie Cao이 [arXiv]에 게시한 ‘Metis: Training Large Language Models with Advanced Low-Bit Quantization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mobile Agents

[논문리뷰] MobiAgent: A Systematic Framework for Customizable Mobile Agents

September 3, 2025

Wangbo Gong이 [arXiv]에 게시한 ‘MobiAgent: A Systematic Framework for Customizable Mobile Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agent Acceleration

[논문리뷰] MobiAgent: A Systematic Framework for Customizable Mobile Agents

September 3, 2025

Wangbo Gong이 [arXiv]에 게시한 ‘MobiAgent: A Systematic Framework for Customizable Mobile Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vision Encoder

[논문리뷰] OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning

September 3, 2025

Zirui Wang이 [arXiv]에 게시한 ‘OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Generative Pretraining

[논문리뷰] OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning

September 3, 2025

Zirui Wang이 [arXiv]에 게시한 ‘OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Captioning Loss

[논문리뷰] OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning

September 3, 2025

Zirui Wang이 [arXiv]에 게시한 ‘OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image-Text Models

[논문리뷰] OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning

September 3, 2025

Zirui Wang이 [arXiv]에 게시한 ‘OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

문서 변환

[논문리뷰] POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion

September 3, 2025

Haicheng Wang이 [arXiv]에 게시한 ‘POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

시각-언어 모델

[논문리뷰] POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion

September 3, 2025

Haicheng Wang이 [arXiv]에 게시한 ‘POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

자가 개선

[논문리뷰] POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion

September 3, 2025

Haicheng Wang이 [arXiv]에 게시한 ‘POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

합성 데이터

[논문리뷰] POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion

September 3, 2025

Haicheng Wang이 [arXiv]에 게시한 ‘POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

증류 없는 학습

[논문리뷰] POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion

September 3, 2025

Haicheng Wang이 [arXiv]에 게시한 ‘POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning Vectors

[논문리뷰] Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic

September 3, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Task Arithmetic

[논문리뷰] Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic

September 3, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Parameter Transfer

[논문리뷰] Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic

September 3, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-to-SQL

[논문리뷰] SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction

September 3, 2025

bindsch이 [arXiv]에 게시한 ‘SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Error Correction

[논문리뷰] SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction

September 3, 2025

bindsch이 [arXiv]에 게시한 ‘SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Query Planning

[논문리뷰] SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction

September 3, 2025

bindsch이 [arXiv]에 게시한 ‘SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Database Interaction

[논문리뷰] SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction

September 3, 2025

bindsch이 [arXiv]에 게시한 ‘SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-turn Reasoning

[논문리뷰] SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning

September 3, 2025

Qian Liu이 [arXiv]에 게시한 ‘SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gradient Explosion

[논문리뷰] SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning

September 3, 2025

Qian Liu이 [arXiv]에 게시한 ‘SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Training Stability

[논문리뷰] SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning

September 3, 2025

Qian Liu이 [arXiv]에 게시한 ‘SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Trajectory Filtering

[논문리뷰] SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning

September 3, 2025

Qian Liu이 [arXiv]에 게시한 ‘SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Zero RL

[논문리뷰] SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning

September 3, 2025

Qian Liu이 [arXiv]에 게시한 ‘SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Metalinguistic Reasoning

[논문리뷰] The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang

September 3, 2025

Solomon Tsai이 [arXiv]에 게시한 ‘The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Constructed Language

[논문리뷰] The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang

September 3, 2025

Solomon Tsai이 [arXiv]에 게시한 ‘The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Camlang

[논문리뷰] The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang

September 3, 2025

Solomon Tsai이 [arXiv]에 게시한 ‘The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Second Language Acquisition

[논문리뷰] The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang

September 3, 2025

Solomon Tsai이 [arXiv]에 게시한 ‘The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sequential Decision Making

[논문리뷰] The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

September 3, 2025

Hejia Geng이 [arXiv]에 게시한 ‘The Landscape of Agentic Reinforcement Learning for LLMs: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Autonomous AI

[논문리뷰] The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

September 3, 2025

Hejia Geng이 [arXiv]에 게시한 ‘The Landscape of Agentic Reinforcement Learning for LLMs: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Point Cloud Learning

[논문리뷰] Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views

September 3, 2025

Junchi Yan이 [arXiv]에 게시한 ‘Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Vie...

Back to Top ↑

Cross Reconstruction

[논문리뷰] Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views

September 3, 2025

Junchi Yan이 [arXiv]에 게시한 ‘Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Vie...

Back to Top ↑

Decoupled Views

[논문리뷰] Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views

September 3, 2025

Junchi Yan이 [arXiv]에 게시한 ‘Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Vie...

Back to Top ↑

Multi-Turn RL

[논문리뷰] UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

September 3, 2025

Haoyang Zou이 [arXiv]에 게시한 ‘UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hybrid Environments

[논문리뷰] UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

September 3, 2025

Haoyang Zou이 [arXiv]에 게시한 ‘UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Parameter Interpolation

[논문리뷰] UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

September 3, 2025

Haoyang Zou이 [arXiv]에 게시한 ‘UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Customizable Strategies

[논문리뷰] Universal Deep Research: Bring Your Own Model and Strategy

September 3, 2025

Pavlo Molchanov이 [arXiv]에 게시한 ‘Universal Deep Research: Bring Your Own Model and Strategy’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

User-Defined Agents

[논문리뷰] Universal Deep Research: Bring Your Own Model and Strategy

September 3, 2025

Pavlo Molchanov이 [arXiv]에 게시한 ‘Universal Deep Research: Bring Your Own Model and Strategy’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sandboxed Execution

[논문리뷰] Universal Deep Research: Bring Your Own Model and Strategy

September 3, 2025

Pavlo Molchanov이 [arXiv]에 게시한 ‘Universal Deep Research: Bring Your Own Model and Strategy’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reinforcement Learning from Verifiable Rewards (RLVR)

[논문리뷰] VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use

September 3, 2025

Zhiheng Lyu이 [arXiv]에 게시한 ‘VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Asynchronous Execution

[논문리뷰] VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use

September 3, 2025

Zhiheng Lyu이 [arXiv]에 게시한 ‘VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-modal AI

[논문리뷰] VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use

September 3, 2025

Zhiheng Lyu이 [arXiv]에 게시한 ‘VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Monocular SLAM

[논문리뷰] ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association

September 3, 2025

Daniel Cremers이 [arXiv]에 게시한 ‘ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dense Reconstruction

[논문리뷰] ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association

September 3, 2025

Daniel Cremers이 [arXiv]에 게시한 ‘ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pose Graph Optimization

[논문리뷰] ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association

September 3, 2025

Daniel Cremers이 [arXiv]에 게시한 ‘ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Intrinsics-free

[논문리뷰] ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association

September 3, 2025

Daniel Cremers이 [arXiv]에 게시한 ‘ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-time

[논문리뷰] ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association

September 3, 2025

Daniel Cremers이 [arXiv]에 게시한 ‘ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Two-view Association

[논문리뷰] ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association

September 3, 2025

Daniel Cremers이 [arXiv]에 게시한 ‘ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Knowledge Acquisition

[논문리뷰] LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations

September 4, 2025

Yoav Gur-Arieh이 [arXiv]에 게시한 ‘LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pretraining Data

[논문리뷰] LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations

September 4, 2025

Yoav Gur-Arieh이 [arXiv]에 게시한 ‘LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Entity Linking

[논문리뷰] LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations

September 4, 2025

Yoav Gur-Arieh이 [arXiv]에 게시한 ‘LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Coreference Resolution

[논문리뷰] LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations

September 4, 2025

Yoav Gur-Arieh이 [arXiv]에 게시한 ‘LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Analysis

[논문리뷰] LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations

September 4, 2025

Yoav Gur-Arieh이 [arXiv]에 게시한 ‘LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Checkpoints

[논문리뷰] LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations

September 4, 2025

Yoav Gur-Arieh이 [arXiv]에 게시한 ‘LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Subject Generation

[논문리뷰] MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement

September 4, 2025

Hualiang Wang이 [arXiv]에 게시한 ‘MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Personalized Image Synthesis

[논문리뷰] MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement

September 4, 2025

Hualiang Wang이 [arXiv]에 게시한 ‘MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semantic Correspondence

[논문리뷰] MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement

September 4, 2025

Hualiang Wang이 [arXiv]에 게시한 ‘MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Attention Disentanglement

[논문리뷰] MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement

September 4, 2025

Hualiang Wang이 [arXiv]에 게시한 ‘MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Face Generation

[논문리뷰] Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation

September 4, 2025

Kai Li이 [arXiv]에 게시한 ‘Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Synthesis

[논문리뷰] Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation

September 4, 2025

Kai Li이 [arXiv]에 게시한 ‘Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semantic Control

[논문리뷰] Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation

September 4, 2025

Kai Li이 [arXiv]에 게시한 ‘Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hierarchical Constraint Satisfaction Problems

[논문리뷰] Open Data Synthesis For Deep Research

September 4, 2025

Zheng Liu이 [arXiv]에 게시한 ‘Open Data Synthesis For Deep Research’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human-Robot Interaction (HRI)

[논문리뷰] Robix: A Unified Model for Robot Interaction, Reasoning and Planning

September 4, 2025

Zixuan Wang이 [arXiv]에 게시한 ‘Robix: A Unified Model for Robot Interaction, Reasoning and Planning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Task Planning

[논문리뷰] Robix: A Unified Model for Robot Interaction, Reasoning and Planning

September 4, 2025

Zixuan Wang이 [arXiv]에 게시한 ‘Robix: A Unified Model for Robot Interaction, Reasoning and Planning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Chain-of-Thought (CoT) Reasoning

[논문리뷰] Robix: A Unified Model for Robot Interaction, Reasoning and Planning

September 4, 2025

Zixuan Wang이 [arXiv]에 게시한 ‘Robix: A Unified Model for Robot Interaction, Reasoning and Planning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Research Agents

[논문리뷰] DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks

September 5, 2025

Jiaxuan Lu이 [arXiv]에 게시한 ‘DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Seminar-Grounded Tasks

[논문리뷰] DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks

September 5, 2025

Jiaxuan Lu이 [arXiv]에 게시한 ‘DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Leakage Prevention

[논문리뷰] DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks

September 5, 2025

Jiaxuan Lu이 [arXiv]에 게시한 ‘DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Ill-Structured Problems

[논문리뷰] DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks

September 5, 2025

Jiaxuan Lu이 [arXiv]에 게시한 ‘DeepResearch Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Embedding

[논문리뷰] Delta Activations: A Representation for Finetuned Large Language Models

September 5, 2025

Ser-Nam Lim이 [arXiv]에 게시한 ‘Delta Activations: A Representation for Finetuned Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Delta Activations

[논문리뷰] Delta Activations: A Representation for Finetuned Large Language Models

September 5, 2025

Ser-Nam Lim이 [arXiv]에 게시한 ‘Delta Activations: A Representation for Finetuned Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Finetuned Models

[논문리뷰] Delta Activations: A Representation for Finetuned Large Language Models

September 5, 2025

Ser-Nam Lim이 [arXiv]에 게시한 ‘Delta Activations: A Representation for Finetuned Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Representation

[논문리뷰] Delta Activations: A Representation for Finetuned Large Language Models

September 5, 2025

Ser-Nam Lim이 [arXiv]에 게시한 ‘Delta Activations: A Representation for Finetuned Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Clustering

[논문리뷰] Delta Activations: A Representation for Finetuned Large Language Models

September 5, 2025

Ser-Nam Lim이 [arXiv]에 게시한 ‘Delta Activations: A Representation for Finetuned Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Additive Property

[논문리뷰] Delta Activations: A Representation for Finetuned Large Language Models

September 5, 2025

Ser-Nam Lim이 [arXiv]에 게시한 ‘Delta Activations: A Representation for Finetuned Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Task Embedding

[논문리뷰] Delta Activations: A Representation for Finetuned Large Language Models

September 5, 2025

Ser-Nam Lim이 [arXiv]에 게시한 ‘Delta Activations: A Representation for Finetuned Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

CAD Generation

[논문리뷰] Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings

September 5, 2025

Meie Fang이 [arXiv]에 게시한 ‘Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vector Graphics

[논문리뷰] Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings

September 5, 2025

Meie Fang이 [arXiv]에 게시한 ‘Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sequence-to-Sequence Learning

[논문리뷰] Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings

September 5, 2025

Meie Fang이 [arXiv]에 게시한 ‘Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Engineering Drawings

[논문리뷰] Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings

September 5, 2025

Meie Fang이 [arXiv]에 게시한 ‘Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Soft Target Loss

[논문리뷰] Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings

September 5, 2025

Meie Fang이 [arXiv]에 게시한 ‘Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dual Decoder

[논문리뷰] Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings

September 5, 2025

Meie Fang이 [arXiv]에 게시한 ‘Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pragmatic Understanding

[논문리뷰] Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth

September 5, 2025

Chi-Li Chen이 [arXiv]에 게시한 ‘Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Drivelology

[논문리뷰] Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth

September 5, 2025

Chi-Li Chen이 [arXiv]에 게시한 ‘Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Contextual Inference

[논문리뷰] Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth

September 5, 2025

Chi-Li Chen이 [arXiv]에 게시한 ‘Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Portrait Animation

[논문리뷰] Durian: Dual Reference-guided Portrait Animation with Attribute Transfer

September 5, 2025

Hanbyul Joo이 [arXiv]에 게시한 ‘Durian: Dual Reference-guided Portrait Animation with Attribute Transfer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Attribute Transfer

[논문리뷰] Durian: Dual Reference-guided Portrait Animation with Attribute Transfer

September 5, 2025

Hanbyul Joo이 [arXiv]에 게시한 ‘Durian: Dual Reference-guided Portrait Animation with Attribute Transfer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dual Reference Networks

[논문리뷰] Durian: Dual Reference-guided Portrait Animation with Attribute Transfer

September 5, 2025

Hanbyul Joo이 [arXiv]에 게시한 ‘Durian: Dual Reference-guided Portrait Animation with Attribute Transfer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Reconstruction

[논문리뷰] Durian: Dual Reference-guided Portrait Animation with Attribute Transfer

September 5, 2025

Hanbyul Joo이 [arXiv]에 게시한 ‘Durian: Dual Reference-guided Portrait Animation with Attribute Transfer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Facial Editing

[논문리뷰] Durian: Dual Reference-guided Portrait Animation with Attribute Transfer

September 5, 2025

Hanbyul Joo이 [arXiv]에 게시한 ‘Durian: Dual Reference-guided Portrait Animation with Attribute Transfer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Malicious Input Detection

[논문리뷰] False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize

September 5, 2025

Muhao Chen이 [arXiv]에 게시한 ‘False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Probing Classifiers

[논문리뷰] False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize

September 5, 2025

Muhao Chen이 [arXiv]에 게시한 ‘False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Superficial Patterns

[논문리뷰] False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize

September 5, 2025

Muhao Chen이 [arXiv]에 게시한 ‘False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Instructional Patterns

[논문리뷰] False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize

September 5, 2025

Muhao Chen이 [arXiv]에 게시한 ‘False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Trigger Words

[논문리뷰] False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize

September 5, 2025

Muhao Chen이 [arXiv]에 게시한 ‘False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Flow-based Models

[논문리뷰] Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

September 5, 2025

Lingxi Xie이 [arXiv]에 게시한 ‘Few-step Flow for 3D Generation via Marginal-Data Transport Distillation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Few-step Sampling

[논문리뷰] Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

September 5, 2025

Lingxi Xie이 [arXiv]에 게시한 ‘Few-step Flow for 3D Generation via Marginal-Data Transport Distillation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Marginal-Data Transport

[논문리뷰] Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

September 5, 2025

Lingxi Xie이 [arXiv]에 게시한 ‘Few-step Flow for 3D Generation via Marginal-Data Transport Distillation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Velocity Matching

[논문리뷰] Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

September 5, 2025

Lingxi Xie이 [arXiv]에 게시한 ‘Few-step Flow for 3D Generation via Marginal-Data Transport Distillation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Velocity Distillation

[논문리뷰] Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

September 5, 2025

Lingxi Xie이 [arXiv]에 게시한 ‘Few-step Flow for 3D Generation via Marginal-Data Transport Distillation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dense Geometry Estimation

[논문리뷰] From Editor to Dense Geometry Estimator

September 5, 2025

Lang Nie이 [arXiv]에 게시한 ‘From Editor to Dense Geometry Estimator’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Normal Estimation

[논문리뷰] From Editor to Dense Geometry Estimator

September 5, 2025

Lang Nie이 [arXiv]에 게시한 ‘From Editor to Dense Geometry Estimator’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Logarithmic Quantization

[논문리뷰] From Editor to Dense Geometry Estimator

September 5, 2025

Lang Nie이 [arXiv]에 게시한 ‘From Editor to Dense Geometry Estimator’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cognitive Inertia

[논문리뷰] Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?

September 5, 2025

Yu Fu이 [arXiv]에 게시한 ‘Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Named Entity Retrieval

[논문리뷰] NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings

September 5, 2025

Oren Glickman이 [arXiv]에 게시한 ‘NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Type-Aware Embeddings

[논문리뷰] NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings

September 5, 2025

Oren Glickman이 [arXiv]에 게시한 ‘NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Internal Representations

[논문리뷰] NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings

September 5, 2025

Oren Glickman이 [arXiv]에 게시한 ‘NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Post-Training

[논문리뷰] Towards a Unified View of Large Language Model Post-Training

September 5, 2025

Hongyi Liu이 [arXiv]에 게시한 ‘Towards a Unified View of Large Language Model Post-Training’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hybrid Algorithms

[논문리뷰] Towards a Unified View of Large Language Model Post-Training

September 5, 2025

Hongyi Liu이 [arXiv]에 게시한 ‘Towards a Unified View of Large Language Model Post-Training’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bias-Variance Tradeoff

[논문리뷰] Towards a Unified View of Large Language Model Post-Training

September 5, 2025

Hongyi Liu이 [arXiv]에 게시한 ‘Towards a Unified View of Large Language Model Post-Training’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Training Objective

[논문리뷰] Transition Models: Rethinking the Generative Learning Objective

September 5, 2025

Yangguang Li이 [arXiv]에 게시한 ‘Transition Models: Rethinking the Generative Learning Objective’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Continuous-Time Dynamics

[논문리뷰] Transition Models: Rethinking the Generative Learning Objective

September 5, 2025

Yangguang Li이 [arXiv]에 게시한 ‘Transition Models: Rethinking the Generative Learning Objective’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

State Transition

[논문리뷰] Transition Models: Rethinking the Generative Learning Objective

September 5, 2025

Yangguang Li이 [arXiv]에 게시한 ‘Transition Models: Rethinking the Generative Learning Objective’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scalable Training

[논문리뷰] Transition Models: Rethinking the Generative Learning Objective

September 5, 2025

Yangguang Li이 [arXiv]에 게시한 ‘Transition Models: Rethinking the Generative Learning Objective’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Segment Selection

[논문리뷰] Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding

September 5, 2025

Lionel Ni이 [arXiv]에 게시한 ‘Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bi-level Reward

[논문리뷰] Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding

September 5, 2025

Lionel Ni이 [arXiv]에 게시한 ‘Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Behavioral Evaluation

[논문리뷰] Behavioral Fingerprinting of Large Language Models

September 8, 2025

Xing Li이 [arXiv]에 게시한 ‘Behavioral Fingerprinting of Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Alignment

[논문리뷰] Behavioral Fingerprinting of Large Language Models

September 8, 2025

Xing Li이 [arXiv]에 게시한 ‘Behavioral Fingerprinting of Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sycophancy

[논문리뷰] Behavioral Fingerprinting of Large Language Models

September 8, 2025

Xing Li이 [arXiv]에 게시한 ‘Behavioral Fingerprinting of Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

World Model Brittleness

[논문리뷰] Behavioral Fingerprinting of Large Language Models

September 8, 2025

Xing Li이 [arXiv]에 게시한 ‘Behavioral Fingerprinting of Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Metacognition

[논문리뷰] Behavioral Fingerprinting of Large Language Models

September 8, 2025

Xing Li이 [arXiv]에 게시한 ‘Behavioral Fingerprinting of Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Personality Profiling

[논문리뷰] Behavioral Fingerprinting of Large Language Models

September 8, 2025

Xing Li이 [arXiv]에 게시한 ‘Behavioral Fingerprinting of Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Autocurriculum

[논문리뷰] Bootstrapping Task Spaces for Self-Improvement

September 8, 2025

Yoram Bachrach이 [arXiv]에 게시한 ‘Bootstrapping Task Spaces for Self-Improvement’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Task-Space Exploration

[논문리뷰] Bootstrapping Task Spaces for Self-Improvement

September 8, 2025

Yoram Bachrach이 [arXiv]에 게시한 ‘Bootstrapping Task Spaces for Self-Improvement’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Inference-Time Iteration

[논문리뷰] Bootstrapping Task Spaces for Self-Improvement

September 8, 2025

Yoram Bachrach이 [arXiv]에 게시한 ‘Bootstrapping Task Spaces for Self-Improvement’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Unreal Engine 5

[논문리뷰] LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation

September 8, 2025

Zhan Zhao이 [arXiv]에 게시한 ‘LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Interactive Environments

[논문리뷰] LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation

September 8, 2025

Zhan Zhao이 [arXiv]에 게시한 ‘LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sim-to-Real

[논문리뷰] LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation

September 8, 2025

Zhan Zhao이 [arXiv]에 게시한 ‘LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spatial Understanding

[논문리뷰] LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation

September 8, 2025

Zhan Zhao이 [arXiv]에 게시한 ‘LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Input

[논문리뷰] LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation

September 8, 2025

Zhan Zhao이 [arXiv]에 게시한 ‘LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Lighting Estimation

[논문리뷰] LuxDiT: Lighting Estimation with Video Diffusion Transformer

September 8, 2025

Sanja Fidler이 [arXiv]에 게시한 ‘LuxDiT: Lighting Estimation with Video Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

HDR Environment Map

[논문리뷰] LuxDiT: Lighting Estimation with Video Diffusion Transformer

September 8, 2025

Sanja Fidler이 [arXiv]에 게시한 ‘LuxDiT: Lighting Estimation with Video Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Transformer

[논문리뷰] LuxDiT: Lighting Estimation with Video Diffusion Transformer

September 8, 2025

Sanja Fidler이 [arXiv]에 게시한 ‘LuxDiT: Lighting Estimation with Video Diffusion Transformer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D CT

[논문리뷰] MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting

September 8, 2025

Vanessa Wildman이 [arXiv]에 게시한 ‘MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting’ 논...

Back to Top ↑

Diagnostic Error Reduction

[논문리뷰] MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting

September 8, 2025

Vanessa Wildman이 [arXiv]에 게시한 ‘MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting’ 논...

Back to Top ↑

Multi-scale Alignment

[논문리뷰] MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting

September 8, 2025

Vanessa Wildman이 [arXiv]에 게시한 ‘MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting’ 논...

Back to Top ↑

Semantic Enrichment

[논문리뷰] MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting

September 8, 2025

Vanessa Wildman이 [arXiv]에 게시한 ‘MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting’ 논...

Back to Top ↑

Radiology Reporting

[논문리뷰] MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting

September 8, 2025

Vanessa Wildman이 [arXiv]에 게시한 ‘MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting’ 논...

Back to Top ↑

Model Robustness

[논문리뷰] On Robustness and Reliability of Benchmark-Based Evaluation of LLMs

September 8, 2025

Kevin Roitero이 [arXiv]에 게시한 ‘On Robustness and Reliability of Benchmark-Based Evaluation of LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Benchmark Reliability

[논문리뷰] On Robustness and Reliability of Benchmark-Based Evaluation of LLMs

September 8, 2025

Kevin Roitero이 [arXiv]에 게시한 ‘On Robustness and Reliability of Benchmark-Based Evaluation of LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Linguistic Variability

[논문리뷰] On Robustness and Reliability of Benchmark-Based Evaluation of LLMs

September 8, 2025

Kevin Roitero이 [arXiv]에 게시한 ‘On Robustness and Reliability of Benchmark-Based Evaluation of LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Language Model Inference

[논문리뷰] Set Block Decoding is a Language Model Inference Accelerator

September 8, 2025

Jeremy Reizenstein이 [arXiv]에 게시한 ‘Set Block Decoding is a Language Model Inference Accelerator’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Acceleration

[논문리뷰] Set Block Decoding is a Language Model Inference Accelerator

September 8, 2025

Jeremy Reizenstein이 [arXiv]에 게시한 ‘Set Block Decoding is a Language Model Inference Accelerator’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Set Block Decoding

[논문리뷰] Set Block Decoding is a Language Model Inference Accelerator

September 8, 2025

Jeremy Reizenstein이 [arXiv]에 게시한 ‘Set Block Decoding is a Language Model Inference Accelerator’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Next Token Prediction

[논문리뷰] Set Block Decoding is a Language Model Inference Accelerator

September 8, 2025

Jeremy Reizenstein이 [arXiv]에 게시한 ‘Set Block Decoding is a Language Model Inference Accelerator’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Masked Token Prediction

[논문리뷰] Set Block Decoding is a Language Model Inference Accelerator

September 8, 2025

Jeremy Reizenstein이 [arXiv]에 게시한 ‘Set Block Decoding is a Language Model Inference Accelerator’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

KV-caching

[논문리뷰] Set Block Decoding is a Language Model Inference Accelerator

September 8, 2025

Jeremy Reizenstein이 [arXiv]에 게시한 ‘Set Block Decoding is a Language Model Inference Accelerator’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Symbolic Graphics Programming

[논문리뷰] Symbolic Graphics Programming with Large Language Models

September 8, 2025

Kaipeng Zhang이 [arXiv]에 게시한 ‘Symbolic Graphics Programming with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

SVG Generation

[논문리뷰] Symbolic Graphics Programming with Large Language Models

September 8, 2025

Kaipeng Zhang이 [arXiv]에 게시한 ‘Symbolic Graphics Programming with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-to-Image Synthesis

[논문리뷰] Symbolic Graphics Programming with Large Language Models

September 8, 2025

Kaipeng Zhang이 [arXiv]에 게시한 ‘Symbolic Graphics Programming with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-Modal Alignment

[논문리뷰] Symbolic Graphics Programming with Large Language Models

September 8, 2025

Kaipeng Zhang이 [arXiv]에 게시한 ‘Symbolic Graphics Programming with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Program Synthesis

[논문리뷰] Symbolic Graphics Programming with Large Language Models

September 8, 2025

Kaipeng Zhang이 [arXiv]에 게시한 ‘Symbolic Graphics Programming with Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Teleoperation

[논문리뷰] U-ARM : Ultra low-cost general teleoperation interface for robot manipulation

September 8, 2025

Junda Huang이 [arXiv]에 게시한 ‘U-ARM : Ultra low-cost general teleoperation interface for robot manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Low-Cost Hardware

[논문리뷰] U-ARM : Ultra low-cost general teleoperation interface for robot manipulation

September 8, 2025

Junda Huang이 [arXiv]에 게시한 ‘U-ARM : Ultra low-cost general teleoperation interface for robot manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Printing

[논문리뷰] U-ARM : Ultra low-cost general teleoperation interface for robot manipulation

September 8, 2025

Junda Huang이 [arXiv]에 게시한 ‘U-ARM : Ultra low-cost general teleoperation interface for robot manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Leader-Follower System

[논문리뷰] U-ARM : Ultra low-cost general teleoperation interface for robot manipulation

September 8, 2025

Junda Huang이 [arXiv]에 게시한 ‘U-ARM : Ultra low-cost general teleoperation interface for robot manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Robotics Interface

[논문리뷰] U-ARM : Ultra low-cost general teleoperation interface for robot manipulation

September 8, 2025

Junda Huang이 [arXiv]에 게시한 ‘U-ARM : Ultra low-cost general teleoperation interface for robot manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Open Source

[논문리뷰] U-ARM : Ultra low-cost general teleoperation interface for robot manipulation

September 8, 2025

Junda Huang이 [arXiv]에 게시한 ‘U-ARM : Ultra low-cost general teleoperation interface for robot manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pretraining

[논문리뷰] Why Language Models Hallucinate

September 8, 2025

Edwin Zhang이 [arXiv]에 게시한 ‘Why Language Models Hallucinate’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Binary Classification

[논문리뷰] Why Language Models Hallucinate

September 8, 2025

Edwin Zhang이 [arXiv]에 게시한 ‘Why Language Models Hallucinate’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Symbolic Music Reasoning

[논문리뷰] WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning

September 8, 2025

Amit Namburi이 [arXiv]에 게시한 ‘WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Music Score Analysis

[논문리뷰] WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning

September 8, 2025

Amit Namburi이 [arXiv]에 게시한 ‘WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

In-the-Wild Data

[논문리뷰] WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning

September 8, 2025

Amit Namburi이 [arXiv]에 게시한 ‘WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Music Theory

[논문리뷰] WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning

September 8, 2025

Amit Namburi이 [arXiv]에 게시한 ‘WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Online 3D Reconstruction

[논문리뷰] WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

September 8, 2025

Wenzheng Chang이 [arXiv]에 게시한 ‘WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Streaming Reconstruction

[논문리뷰] WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

September 8, 2025

Wenzheng Chang이 [arXiv]에 게시한 ‘WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sliding Window

[논문리뷰] WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

September 8, 2025

Wenzheng Chang이 [arXiv]에 게시한 ‘WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Camera Token Pool

[논문리뷰] WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

September 8, 2025

Wenzheng Chang이 [arXiv]에 게시한 ‘WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-time Performance

[논문리뷰] WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

September 8, 2025

Wenzheng Chang이 [arXiv]에 게시한 ‘WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dark Humor Detection

[논문리뷰] D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning

September 9, 2025

Dhanvin Sanjay Namboodiri이 [arXiv]에 게시한 ‘D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Iterative Reasoning Refinement

[논문리뷰] D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning

September 9, 2025

Dhanvin Sanjay Namboodiri이 [arXiv]에 게시한 ‘D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Meme Analysis

[논문리뷰] D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning

September 9, 2025

Dhanvin Sanjay Namboodiri이 [arXiv]에 게시한 ‘D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-Modal Attention

[논문리뷰] D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning

September 9, 2025

Dhanvin Sanjay Namboodiri이 [arXiv]에 게시한 ‘D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

2D/3D Classification

[논문리뷰] Does DINOv3 Set a New Medical Vision Standard?

September 9, 2025

Bailiang Jian이 [arXiv]에 게시한 ‘Does DINOv3 Set a New Medical Vision Standard?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Segmentation

[논문리뷰] Does DINOv3 Set a New Medical Vision Standard?

September 9, 2025

Bailiang Jian이 [arXiv]에 게시한 ‘Does DINOv3 Set a New Medical Vision Standard?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

T2I Benchmarking

[논문리뷰] Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?

September 9, 2025

Rui Chen이 [arXiv]에 게시한 ‘Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Compositional Reasoning

[논문리뷰] Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?

September 9, 2025

Rui Chen이 [arXiv]에 게시한 ‘Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Deductive Inference

[논문리뷰] Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?

September 9, 2025

Rui Chen이 [arXiv]에 게시한 ‘Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Inductive Inference

[논문리뷰] Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?

September 9, 2025

Rui Chen이 [arXiv]에 게시한 ‘Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Abductive Inference

[논문리뷰] Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?

September 9, 2025

Rui Chen이 [arXiv]에 게시한 ‘Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

MLLM Evaluation

[논문리뷰] Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?

September 9, 2025

Rui Chen이 [arXiv]에 게시한 ‘Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Noise Suppression

[논문리뷰] Focusing by Contrastive Attention: Enhancing VLMs’ Visual Reasoning

September 9, 2025

Baolong Bi이 [arXiv]에 게시한 ‘Focusing by Contrastive Attention: Enhancing VLMs’ Visual Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Complexity

[논문리뷰] Focusing by Contrastive Attention: Enhancing VLMs’ Visual Reasoning

September 9, 2025

Baolong Bi이 [arXiv]에 게시한 ‘Focusing by Contrastive Attention: Enhancing VLMs’ Visual Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Interleaving Reasoning

[논문리뷰] Interleaving Reasoning for Better Text-to-Image Generation

September 9, 2025

Shixiang Tang이 [arXiv]에 게시한 ‘Interleaving Reasoning for Better Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fine-grained Detail

[논문리뷰] Interleaving Reasoning for Better Text-to-Image Generation

September 9, 2025

Shixiang Tang이 [arXiv]에 게시한 ‘Interleaving Reasoning for Better Text-to-Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multilingual LLM

[논문리뷰] Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian

September 9, 2025

Hoi-Fong Mak이 [arXiv]에 게시한 ‘Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Low-Resource Language

[논문리뷰] Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian

September 9, 2025

Hoi-Fong Mak이 [arXiv]에 게시한 ‘Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

German

[논문리뷰] Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian

September 9, 2025

Hoi-Fong Mak이 [arXiv]에 게시한 ‘Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bavarian Dialect

[논문리뷰] Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian

September 9, 2025

Hoi-Fong Mak이 [arXiv]에 게시한 ‘Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-Lingual Transfer

[논문리뷰] Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian

September 9, 2025

Hoi-Fong Mak이 [arXiv]에 게시한 ‘Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Continuous Pretraining

[논문리뷰] Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian

September 9, 2025

Hoi-Fong Mak이 [arXiv]에 게시한 ‘Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Llama-3.1

[논문리뷰] Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian

September 9, 2025

Hoi-Fong Mak이 [arXiv]에 게시한 ‘Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Expansion

[논문리뷰] Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian

September 9, 2025

Hoi-Fong Mak이 [arXiv]에 게시한 ‘Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mobile GUI Agents

[논문리뷰] MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents

September 9, 2025

Zhengxi Lu이 [arXiv]에 게시한 ‘MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hybrid Automation

[논문리뷰] MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents

September 9, 2025

Zhengxi Lu이 [arXiv]에 게시한 ‘MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Shortcut Generation

[논문리뷰] MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents

September 9, 2025

Zhengxi Lu이 [arXiv]에 게시한 ‘MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Task Efficiency

[논문리뷰] MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents

September 9, 2025

Zhengxi Lu이 [arXiv]에 게시한 ‘MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mobile Robotics

[논문리뷰] MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents

September 9, 2025

Zhengxi Lu이 [arXiv]에 게시한 ‘MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Research Reproducibility

[논문리뷰] Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents

September 9, 2025

James Zou이 [arXiv]에 게시한 ‘Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scientific Communication

[논문리뷰] Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents

September 9, 2025

James Zou이 [arXiv]에 게시한 ‘Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Genomics

[논문리뷰] Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents

September 9, 2025

James Zou이 [arXiv]에 게시한 ‘Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Single-Cell Analysis

[논문리뷰] Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents

September 9, 2025

James Zou이 [arXiv]에 게시한 ‘Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spatial Transcriptomics

[논문리뷰] Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents

September 9, 2025

James Zou이 [arXiv]에 게시한 ‘Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Tool Usage

[논문리뷰] Reinforced Visual Perception with Tools

September 9, 2025

Mingyang Fu이 [arXiv]에 게시한 ‘Reinforced Visual Perception with Tools’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Perception-heavy Benchmarks

[논문리뷰] Reinforced Visual Perception with Tools

September 9, 2025

Mingyang Fu이 [arXiv]에 게시한 ‘Reinforced Visual Perception with Tools’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vision Tools

[논문리뷰] Reinforced Visual Perception with Tools

September 9, 2025

Mingyang Fu이 [arXiv]에 게시한 ‘Reinforced Visual Perception with Tools’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Deep Research Systems

[논문리뷰] Reinforcement Learning Foundations for Deep Research Systems: A Survey

September 9, 2025

Wei Han이 [arXiv]에 게시한 ‘Reinforcement Learning Foundations for Deep Research Systems: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hierarchical Agents

[논문리뷰] Reinforcement Learning Foundations for Deep Research Systems: A Survey

September 9, 2025

Wei Han이 [arXiv]에 게시한 ‘Reinforcement Learning Foundations for Deep Research Systems: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

RL Frameworks

[논문리뷰] Reinforcement Learning Foundations for Deep Research Systems: A Survey

September 9, 2025

Wei Han이 [arXiv]에 게시한 ‘Reinforcement Learning Foundations for Deep Research Systems: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Open-Ended Generation

[논문리뷰] Reverse-Engineered Reasoning for Open-Ended Generation

September 9, 2025

Wangchunshu Zhou이 [arXiv]에 게시한 ‘Reverse-Engineered Reasoning for Open-Ended Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reverse-Engineered Reasoning (REER)

[논문리뷰] Reverse-Engineered Reasoning for Open-Ended Generation

September 9, 2025

Wangchunshu Zhou이 [arXiv]에 게시한 ‘Reverse-Engineered Reasoning for Open-Ended Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Perplexity Minimization

[논문리뷰] Reverse-Engineered Reasoning for Open-Ended Generation

September 9, 2025

Wangchunshu Zhou이 [arXiv]에 게시한 ‘Reverse-Engineered Reasoning for Open-Ended Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

DeepWriting-20K

[논문리뷰] Reverse-Engineered Reasoning for Open-Ended Generation

September 9, 2025

Wangchunshu Zhou이 [arXiv]에 게시한 ‘Reverse-Engineered Reasoning for Open-Ended Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Trajectory-aware RL

[논문리뷰] Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

September 9, 2025

Ke Shen이 [arXiv]에 게시한 ‘Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Value Model

[논문리뷰] Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

September 9, 2025

Ke Shen이 [arXiv]에 게시한 ‘Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Masked Diffusion Models

[논문리뷰] Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

September 9, 2025

Ke Shen이 [arXiv]에 게시한 ‘Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Resistant AI

[논문리뷰] R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World

September 9, 2025

Bowen Zhou이 [arXiv]에 게시한 ‘R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Resilient AI

[논문리뷰] R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World

September 9, 2025

Bowen Zhou이 [arXiv]에 게시한 ‘R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Coevolution

[논문리뷰] R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World

September 9, 2025

Bowen Zhou이 [arXiv]에 게시한 ‘R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fast-Slow Models

[논문리뷰] R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World

September 9, 2025

Bowen Zhou이 [arXiv]에 게시한 ‘R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AGI Alignment

[논문리뷰] R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World

September 9, 2025

Bowen Zhou이 [arXiv]에 게시한 ‘R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

TPTP Ecosystem

[논문리뷰] Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem

September 9, 2025

Damien Sileo이 [arXiv]에 게시한 ‘Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Saturation Proving

[논문리뷰] Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem

September 9, 2025

Damien Sileo이 [arXiv]에 게시한 ‘Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Proof Graph Reconstruction

[논문리뷰] Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem

September 9, 2025

Damien Sileo이 [arXiv]에 게시한 ‘Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Step-Provers

[논문리뷰] Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers

September 9, 2025

Xia Xiao이 [arXiv]에 게시한 ‘Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Off-Policy RL

[논문리뷰] Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers

September 9, 2025

Xia Xiao이 [arXiv]에 게시한 ‘Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Automated Theorem Proving (ATP)

[논문리뷰] Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers

September 9, 2025

Xia Xiao이 [arXiv]에 게시한 ‘Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Formal Mathematics

[논문리뷰] Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers

September 9, 2025

Xia Xiao이 [arXiv]에 게시한 ‘Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AlphaZero

[논문리뷰] Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers

September 9, 2025

Xia Xiao이 [arXiv]에 게시한 ‘Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Knowledge-Intensive Tasks

[논문리뷰] Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet

September 9, 2025

See-Kiong Ng이 [arXiv]에 게시한 ‘Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Unified Audio-Video Generation

[논문리뷰] UniVerse-1: Unified Audio-Video Generation via Stitching of Experts

September 9, 2025

Xinyao Liao이 [arXiv]에 게시한 ‘UniVerse-1: Unified Audio-Video Generation via Stitching of Experts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Stitching of Experts (SoE)

[논문리뷰] UniVerse-1: Unified Audio-Video Generation via Stitching of Experts

September 9, 2025

Xinyao Liao이 [arXiv]에 게시한 ‘UniVerse-1: Unified Audio-Video Generation via Stitching of Experts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Diffusion

[논문리뷰] UniVerse-1: Unified Audio-Video Generation via Stitching of Experts

September 9, 2025

Xinyao Liao이 [arXiv]에 게시한 ‘UniVerse-1: Unified Audio-Video Generation via Stitching of Experts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Online Annotation

[논문리뷰] UniVerse-1: Unified Audio-Video Generation via Stitching of Experts

September 9, 2025

Xinyao Liao이 [arXiv]에 게시한 ‘UniVerse-1: Unified Audio-Video Generation via Stitching of Experts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-modal Noise Correlation

[논문리뷰] UniVerse-1: Unified Audio-Video Generation via Stitching of Experts

September 9, 2025

Xinyao Liao이 [arXiv]에 게시한 ‘UniVerse-1: Unified Audio-Video Generation via Stitching of Experts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Verse-Bench

[논문리뷰] UniVerse-1: Unified Audio-Video Generation via Stitching of Experts

September 9, 2025

Xinyao Liao이 [arXiv]에 게시한 ‘UniVerse-1: Unified Audio-Video Generation via Stitching of Experts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Web Navigation

[논문리뷰] WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents

September 9, 2025

Aili Chen이 [arXiv]에 게시한 ‘WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Causal Attention

[논문리뷰] Causal Attention with Lookahead Keys

September 10, 2025

Quanquan Gu이 [arXiv]에 게시한 ‘Causal Attention with Lookahead Keys’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Lookahead Keys

[논문리뷰] Causal Attention with Lookahead Keys

September 10, 2025

Quanquan Gu이 [arXiv]에 게시한 ‘Causal Attention with Lookahead Keys’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Autoregressive Modeling

[논문리뷰] Causal Attention with Lookahead Keys

September 10, 2025

Quanquan Gu이 [arXiv]에 게시한 ‘Causal Attention with Lookahead Keys’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Perplexity Reduction

[논문리뷰] Causal Attention with Lookahead Keys

September 10, 2025

Quanquan Gu이 [arXiv]에 게시한 ‘Causal Attention with Lookahead Keys’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Radiology

[논문리뷰] Curia: A Multi-Modal Foundation Model for Radiology

September 10, 2025

Elodie Ferreres이 [arXiv]에 게시한 ‘Curia: A Multi-Modal Foundation Model for Radiology’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Computed Tomography (CT)

[논문리뷰] Curia: A Multi-Modal Foundation Model for Radiology

September 10, 2025

Elodie Ferreres이 [arXiv]에 게시한 ‘Curia: A Multi-Modal Foundation Model for Radiology’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Magnetic Resonance Imaging (MRI)

[논문리뷰] Curia: A Multi-Modal Foundation Model for Radiology

September 10, 2025

Elodie Ferreres이 [arXiv]에 게시한 ‘Curia: A Multi-Modal Foundation Model for Radiology’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-Modality Generalization

[논문리뷰] Curia: A Multi-Modal Foundation Model for Radiology

September 10, 2025

Elodie Ferreres이 [arXiv]에 게시한 ‘Curia: A Multi-Modal Foundation Model for Radiology’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human Preference

[논문리뷰] Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

September 10, 2025

Yingfang Zhang이 [arXiv]에 게시한 ‘Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Direct-Align

[논문리뷰] Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

September 10, 2025

Yingfang Zhang이 [arXiv]에 게시한 ‘Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

SRPO

[논문리뷰] Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

September 10, 2025

Yingfang Zhang이 [arXiv]에 게시한 ‘Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fine-Grained Control

[논문리뷰] Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

September 10, 2025

Yingfang Zhang이 [arXiv]에 게시한 ‘Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Flow Matching Models

[논문리뷰] Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

September 10, 2025

Yingfang Zhang이 [arXiv]에 게시한 ‘Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vision-Language-Action

[논문리뷰] F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions

September 10, 2025

Zherui Qiu이 [arXiv]에 게시한 ‘F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Foresight

[논문리뷰] F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions

September 10, 2025

Zherui Qiu이 [arXiv]에 게시한 ‘F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Predictive Inverse Dynamics

[논문리뷰] F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions

September 10, 2025

Zherui Qiu이 [arXiv]에 게시한 ‘F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mixture-of-Transformer

[논문리뷰] F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions

September 10, 2025

Zherui Qiu이 [arXiv]에 게시한 ‘F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-stage Training

[논문리뷰] F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions

September 10, 2025

Zherui Qiu이 [arXiv]에 게시한 ‘F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data-Free Training

[논문리뷰] Language Self-Play For Data-Free Training

September 10, 2025

Vijai Mohan이 [arXiv]에 게시한 ‘Language Self-Play For Data-Free Training’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Search

[논문리뷰] Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search

September 10, 2025

Tianjian Li이 [arXiv]에 게시한 ‘Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Tool-Integrated Agents

[논문리뷰] Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search

September 10, 2025

Tianjian Li이 [arXiv]에 게시한 ‘Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Exploratory Reasoning

[논문리뷰] Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search

September 10, 2025

Tianjian Li이 [arXiv]에 게시한 ‘Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Over-turn Masking

[논문리뷰] Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search

September 10, 2025

Tianjian Li이 [arXiv]에 게시한 ‘Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Parallel Thinking

[논문리뷰] Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

September 10, 2025

Xinyu Yang이 [arXiv]에 게시한 ‘Parallel-R1: Towards Parallel Thinking via Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Progressive Curriculum

[논문리뷰] Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

September 10, 2025

Xinyu Yang이 [arXiv]에 게시한 ‘Parallel-R1: Towards Parallel Thinking via Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Exploration Scaffold

[논문리뷰] Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

September 10, 2025

Xinyu Yang이 [arXiv]에 게시한 ‘Parallel-R1: Towards Parallel Thinking via Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Noise Scheduling

[논문리뷰] Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling

September 10, 2025

Diana Marculescu이 [arXiv]에 게시한 ‘Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Post-Training Quantization

[논문리뷰] Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling

September 10, 2025

Diana Marculescu이 [arXiv]에 게시한 ‘Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image Quality Metrics

[논문리뷰] Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling

September 10, 2025

Diana Marculescu이 [arXiv]에 게시한 ‘Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Latent Consistency Models

[논문리뷰] Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling

September 10, 2025

Diana Marculescu이 [arXiv]에 게시한 ‘Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Unified Multimodal Models

[논문리뷰] Reconstruction Alignment Improves Unified Multimodal Models

September 10, 2025

XuDong Wang이 [arXiv]에 게시한 ‘Reconstruction Alignment Improves Unified Multimodal Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reconstruction Alignment

[논문리뷰] Reconstruction Alignment Improves Unified Multimodal Models

September 10, 2025

XuDong Wang이 [arXiv]에 게시한 ‘Reconstruction Alignment Improves Unified Multimodal Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Embeddings

[논문리뷰] Reconstruction Alignment Improves Unified Multimodal Models

September 10, 2025

XuDong Wang이 [arXiv]에 게시한 ‘Reconstruction Alignment Improves Unified Multimodal Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Factuality

[논문리뷰] SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge

September 10, 2025

Dipanjan Das이 [arXiv]에 게시한 ‘SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Parametric Knowledge

[논문리뷰] SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge

September 10, 2025

Dipanjan Das이 [arXiv]에 게시한 ‘SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hint Scaffolding

[논문리뷰] Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding

September 10, 2025

Yongcheng Zeng이 [arXiv]에 게시한 ‘Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Item Response Theory

[논문리뷰] Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding

September 10, 2025

Yongcheng Zeng이 [arXiv]에 게시한 ‘Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Exploration Efficiency

[논문리뷰] Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding

September 10, 2025

Yongcheng Zeng이 [arXiv]에 게시한 ‘Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Problem Difficulty

[논문리뷰] Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding

September 10, 2025

Yongcheng Zeng이 [arXiv]에 게시한 ‘Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Identity Generation

[논문리뷰] UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward

September 10, 2025

Fei Ding이 [arXiv]에 게시한 ‘UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Identity Consistency

[논문리뷰] UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward

September 10, 2025

Fei Ding이 [arXiv]에 게시한 ‘UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Identity Confusion

[논문리뷰] UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward

September 10, 2025

Fei Ding이 [arXiv]에 게시한 ‘UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Matching Reward

[논문리뷰] UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward

September 10, 2025

Fei Ding이 [arXiv]에 게시한 ‘UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Global Assignment

[논문리뷰] UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward

September 10, 2025

Fei Ding이 [arXiv]에 게시한 ‘UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Representation Alignment

[논문리뷰] Visual Representation Alignment for Multimodal Large Language Models

September 10, 2025

Heeseong Shin이 [arXiv]에 게시한 ‘Visual Representation Alignment for Multimodal Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fine-grained Visual Understanding

[논문리뷰] Visual Representation Alignment for Multimodal Large Language Models

September 10, 2025

Heeseong Shin이 [arXiv]에 게시한 ‘Visual Representation Alignment for Multimodal Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Object Counting

[논문리뷰] Visual Representation Alignment for Multimodal Large Language Models

September 10, 2025

Heeseong Shin이 [arXiv]에 게시한 ‘Visual Representation Alignment for Multimodal Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gradient Variance

[논문리뷰] ΔL Normalization: Rethink Loss Aggregation in RLVR

September 10, 2025

Lili Qiu이 [arXiv]에 게시한 ‘ΔL Normalization: Rethink Loss Aggregation in RLVR’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Unbiased Estimator

[논문리뷰] ΔL Normalization: Rethink Loss Aggregation in RLVR

September 10, 2025

Lili Qiu이 [arXiv]에 게시한 ‘ΔL Normalization: Rethink Loss Aggregation in RLVR’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D World Modeling

[논문리뷰] 3D and 4D World Modeling: A Survey

September 11, 2025

Ao Liang이 [arXiv]에 게시한 ‘3D and 4D World Modeling: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Predictive Models

[논문리뷰] 3D and 4D World Modeling: A Survey

September 11, 2025

Ao Liang이 [arXiv]에 게시한 ‘3D and 4D World Modeling: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LiDAR

[논문리뷰] 3D and 4D World Modeling: A Survey

September 11, 2025

Ao Liang이 [arXiv]에 게시한 ‘3D and 4D World Modeling: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Occupancy Grids

[논문리뷰] 3D and 4D World Modeling: A Survey

September 11, 2025

Ao Liang이 [arXiv]에 게시한 ‘3D and 4D World Modeling: A Survey’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long-Horizon Decision Making

[논문리뷰] AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning

September 11, 2025

Honglin Guo이 [arXiv]에 게시한 ‘AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Progressive Scaling

[논문리뷰] AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning

September 11, 2025

Honglin Guo이 [arXiv]에 게시한 ‘AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Code Repository

[논문리뷰] EnvX: Agentize Everything with Agentic AI

September 11, 2025

Wenzheng Tom Tang이 [arXiv]에 게시한 ‘EnvX: Agentize Everything with Agentic AI’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agentization

[논문리뷰] EnvX: Agentize Everything with Agentic AI

September 11, 2025

Wenzheng Tom Tang이 [arXiv]에 게시한 ‘EnvX: Agentize Everything with Agentic AI’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agent-to-Agent Protocol

[논문리뷰] EnvX: Agentize Everything with Agentic AI

September 11, 2025

Wenzheng Tom Tang이 [arXiv]에 게시한 ‘EnvX: Agentize Everything with Agentic AI’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human Agency

[논문리뷰] HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants

September 11, 2025

Jacy Reese Anthis이 [arXiv]에 게시한 ‘HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AI Assistants

[논문리뷰] HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants

September 11, 2025

Jacy Reese Anthis이 [arXiv]에 게시한 ‘HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sociotechnical AI

[논문리뷰] HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants

September 11, 2025

Jacy Reese Anthis이 [arXiv]에 게시한 ‘HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AI Alignment

[논문리뷰] HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants

September 11, 2025

Jacy Reese Anthis이 [arXiv]에 게시한 ‘HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scalable Evaluation

[논문리뷰] HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants

September 11, 2025

Jacy Reese Anthis이 [arXiv]에 게시한 ‘HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Weak-to-Strong Learning

[논문리뷰] Hunyuan-MT Technical Report

September 11, 2025

Yang Du이 [arXiv]에 게시한 ‘Hunyuan-MT Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Part Segmentation

[논문리뷰] P3-SAM: Native 3D Part Segmentation

September 11, 2025

Yunhan Yang이 [arXiv]에 게시한 ‘P3-SAM: Native 3D Part Segmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Point Cloud Segmentation

[논문리뷰] P3-SAM: Native 3D Part Segmentation

September 11, 2025

Yunhan Yang이 [arXiv]에 게시한 ‘P3-SAM: Native 3D Part Segmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Prompt-based Segmentation

[논문리뷰] P3-SAM: Native 3D Part Segmentation

September 11, 2025

Yunhan Yang이 [arXiv]에 게시한 ‘P3-SAM: Native 3D Part Segmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Interactive Segmentation

[논문리뷰] P3-SAM: Native 3D Part Segmentation

September 11, 2025

Yunhan Yang이 [arXiv]에 게시한 ‘P3-SAM: Native 3D Part Segmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Automatic Segmentation

[논문리뷰] P3-SAM: Native 3D Part Segmentation

September 11, 2025

Yunhan Yang이 [arXiv]에 게시한 ‘P3-SAM: Native 3D Part Segmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Native 3D

[논문리뷰] P3-SAM: Native 3D Part Segmentation

September 11, 2025

Yunhan Yang이 [arXiv]에 게시한 ‘P3-SAM: Native 3D Part Segmentation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

VLM

[논문리뷰] RewardDance: Reward Scaling in Visual Generation

September 11, 2025

Liang Li이 [arXiv]에 게시한 ‘RewardDance: Reward Scaling in Visual Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reward Scaling

[논문리뷰] RewardDance: Reward Scaling in Visual Generation

September 11, 2025

Liang Li이 [arXiv]에 게시한 ‘RewardDance: Reward Scaling in Visual Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Generative Paradigm

[논문리뷰] RewardDance: Reward Scaling in Visual Generation

September 11, 2025

Liang Li이 [arXiv]에 게시한 ‘RewardDance: Reward Scaling in Visual Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Context Scaling

[논문리뷰] RewardDance: Reward Scaling in Visual Generation

September 11, 2025

Liang Li이 [arXiv]에 게시한 ‘RewardDance: Reward Scaling in Visual Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Toxic Text Generation

[논문리뷰] So let's replace this phrase with insult... Lessons learned from generation of toxic texts with LLMs

September 11, 2025

Alexander Panchenko이 [arXiv]에 게시한 ‘ So let's replace this phrase with insult... Lessons learned from generation of toxic texts with LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text Detoxification

[논문리뷰] So let's replace this phrase with insult... Lessons learned from generation of toxic texts with LLMs

September 11, 2025

Alexander Panchenko이 [arXiv]에 게시한 ‘ So let's replace this phrase with insult... Lessons learned from generation of toxic texts with LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Lexical Diversity

[논문리뷰] So let's replace this phrase with insult... Lessons learned from generation of toxic texts with LLMs

September 11, 2025

Alexander Panchenko이 [arXiv]에 게시한 ‘ So let's replace this phrase with insult... Lessons learned from generation of toxic texts with LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human Annotation

[논문리뷰] So let's replace this phrase with insult... Lessons learned from generation of toxic texts with LLMs

September 11, 2025

Alexander Panchenko이 [arXiv]에 게시한 ‘ So let's replace this phrase with insult... Lessons learned from generation of toxic texts with LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

2D Gaussian Splatting

[논문리뷰] 2D Gaussian Splatting with Semantic Alignment for Image Inpainting

September 12, 2025

Guangming Lu이 [arXiv]에 게시한 ‘2D Gaussian Splatting with Semantic Alignment for Image Inpainting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

DINO Features

[논문리뷰] 2D Gaussian Splatting with Semantic Alignment for Image Inpainting

September 12, 2025

Guangming Lu이 [arXiv]에 게시한 ‘2D Gaussian Splatting with Semantic Alignment for Image Inpainting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Patch-level Rasterization

[논문리뷰] 2D Gaussian Splatting with Semantic Alignment for Image Inpainting

September 12, 2025

Guangming Lu이 [arXiv]에 게시한 ‘2D Gaussian Splatting with Semantic Alignment for Image Inpainting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Continuous Representation

[논문리뷰] 2D Gaussian Splatting with Semantic Alignment for Image Inpainting

September 12, 2025

Guangming Lu이 [arXiv]에 게시한 ‘2D Gaussian Splatting with Semantic Alignment for Image Inpainting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Auto-Encoder

[논문리뷰] Can Understanding and Generation Truly Benefit Together – or Just Coexist?

September 12, 2025

Hui Han이 [arXiv]에 게시한 ‘Can Understanding and Generation Truly Benefit Together – or Just Coexist?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image-to-Text

[논문리뷰] Can Understanding and Generation Truly Benefit Together – or Just Coexist?

September 12, 2025

Hui Han이 [arXiv]에 게시한 ‘Can Understanding and Generation Truly Benefit Together – or Just Coexist?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reconstruction Fidelity

[논문리뷰] Can Understanding and Generation Truly Benefit Together – or Just Coexist?

September 12, 2025

Hui Han이 [arXiv]에 게시한 ‘Can Understanding and Generation Truly Benefit Together – or Just Coexist?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Speech-to-Speech LLMs

[논문리뷰] EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs

September 12, 2025

Kaiqi Kou이 [arXiv]에 게시한 ‘EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Acoustic-Semantic Gap

[논문리뷰] EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs

September 12, 2025

Kaiqi Kou이 [arXiv]에 게시한 ‘EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Echo Training

[논문리뷰] EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs

September 12, 2025

Kaiqi Kou이 [arXiv]에 게시한 ‘EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Unit Language

[논문리뷰] EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs

September 12, 2025

Kaiqi Kou이 [arXiv]에 게시한 ‘EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Knowledge-based QA

[논문리뷰] EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs

September 12, 2025

Kaiqi Kou이 [arXiv]에 게시한 ‘EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning Dataset

[논문리뷰] FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark

September 12, 2025

Shuai Bai이 [arXiv]에 게시한 ‘FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Generation Chain-of-Thought

[논문리뷰] FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark

September 12, 2025

Shuai Bai이 [arXiv]에 게시한 ‘FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image Aesthetics

[논문리뷰] FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark

September 12, 2025

Shuai Bai이 [arXiv]에 게시한 ‘FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Prompt Alignment

[논문리뷰] FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark

September 12, 2025

Shuai Bai이 [arXiv]에 게시한 ‘FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-based Person Retrieval

[논문리뷰] Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval

September 12, 2025

Kaicheng Yang이 [arXiv]에 게시한 ‘Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dual-Masking

[논문리뷰] Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval

September 12, 2025

Kaicheng Yang이 [arXiv]에 게시한 ‘Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gradient-Attention

[논문리뷰] Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval

September 12, 2025

Kaicheng Yang이 [arXiv]에 게시한 ‘Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

WebPerson Dataset

[논문리뷰] Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval

September 12, 2025

Kaicheng Yang이 [arXiv]에 게시한 ‘Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Policy Gradients

[논문리뷰] Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents

September 12, 2025

Xintao Wang이 [arXiv]에 게시한 ‘Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Entropy Modulation

[논문리뷰] Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents

September 12, 2025

Xintao Wang이 [arXiv]에 게시한 ‘Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Credit Assignment

[논문리뷰] Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents

September 12, 2025

Xintao Wang이 [arXiv]에 게시한 ‘Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Uncertainty

[논문리뷰] Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents

September 12, 2025

Xintao Wang이 [arXiv]에 게시한 ‘Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Calibrating Gradient Scaling

[논문리뷰] Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents

September 12, 2025

Xintao Wang이 [arXiv]에 게시한 ‘Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human-Centric Video Generation

[논문리뷰] HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

September 12, 2025

Zhuowei Chen이 [arXiv]에 게시한 ‘HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Conditioning

[논문리뷰] HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

September 12, 2025

Zhuowei Chen이 [arXiv]에 게시한 ‘HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Audio-to-Video

[논문리뷰] HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

September 12, 2025

Zhuowei Chen이 [arXiv]에 게시한 ‘HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Subject Preservation

[논문리뷰] HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

September 12, 2025

Zhuowei Chen이 [arXiv]에 게시한 ‘HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Audio-Visual Synchronization

[논문리뷰] HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

September 12, 2025

Zhuowei Chen이 [arXiv]에 게시한 ‘HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Avatar Animation

[논문리뷰] Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis

September 12, 2025

Wentao Hu이 [arXiv]에 게시한 ‘Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Instructions

[논문리뷰] Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis

September 12, 2025

Wentao Hu이 [arXiv]에 게시한 ‘Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long-Duration Video Generation

[논문리뷰] Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis

September 12, 2025

Wentao Hu이 [arXiv]에 게시한 ‘Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

MLLM Director

[논문리뷰] Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis

September 12, 2025

Wentao Hu이 [arXiv]에 게시한 ‘Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cascaded Framework

[논문리뷰] Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis

September 12, 2025

Wentao Hu이 [arXiv]에 게시한 ‘Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Lip Synchronization

[논문리뷰] Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis

September 12, 2025

Wentao Hu이 [arXiv]에 게시한 ‘Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Instruction Grounding

[논문리뷰] Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis

September 12, 2025

Wentao Hu이 [arXiv]에 게시한 ‘Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Diffusion Transformers

[논문리뷰] Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis

September 12, 2025

Wentao Hu이 [arXiv]에 게시한 ‘Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long-Context LLMs

[논문리뷰] LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering

September 12, 2025

Jianguo Zhang이 [arXiv]에 게시한 ‘LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Code Evaluation

[논문리뷰] LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering

September 12, 2025

Jianguo Zhang이 [arXiv]에 게시한 ‘LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-file Reasoning

[논문리뷰] LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering

September 12, 2025

Jianguo Zhang이 [arXiv]에 게시한 ‘LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Architectural Understanding

[논문리뷰] LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering

September 12, 2025

Jianguo Zhang이 [arXiv]에 게시한 ‘LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Software Development Lifecycle

[논문리뷰] LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering

September 12, 2025

Jianguo Zhang이 [arXiv]에 게시한 ‘LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Metrics

[논문리뷰] LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering

September 12, 2025

Jianguo Zhang이 [arXiv]에 게시한 ‘LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Recommendation

[논문리뷰] Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation

September 12, 2025

Dong-Ho Lee이 [arXiv]에 게시한 ‘Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Modality Alignment

[논문리뷰] Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation

September 12, 2025

Dong-Ho Lee이 [arXiv]에 게시한 ‘Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dilated Convolution

[논문리뷰] Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation

September 12, 2025

Dong-Ho Lee이 [arXiv]에 게시한 ‘Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Maximum Mean Discrepancy

[논문리뷰] Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation

September 12, 2025

Dong-Ho Lee이 [arXiv]에 게시한 ‘Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dimensionality Reduction

[논문리뷰] Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation

September 12, 2025

Dong-Ho Lee이 [arXiv]에 게시한 ‘Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Grounding

[논문리뷰] OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning

September 12, 2025

Yuzheng Zhuang이 [arXiv]에 게시한 ‘OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Task-Adaptive Reasoning

[논문리뷰] OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning

September 12, 2025

Yuzheng Zhuang이 [arXiv]에 게시한 ‘OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Embodiment-Aware Planning

[논문리뷰] OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning

September 12, 2025

Yuzheng Zhuang이 [arXiv]에 게시한 ‘OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM Security

[논문리뷰] Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated

September 12, 2025

Jamie Hayes이 [arXiv]에 게시한 ‘Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Poisoning

[논문리뷰] Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated

September 12, 2025

Jamie Hayes이 [arXiv]에 게시한 ‘Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Backdoor Attacks

[논문리뷰] Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated

September 12, 2025

Jamie Hayes이 [arXiv]에 게시한 ‘Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

CoT Unfaithfulness

[논문리뷰] Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated

September 12, 2025

Jamie Hayes이 [arXiv]에 게시한 ‘Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Emergent Robustness

[논문리뷰] Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated

September 12, 2025

Jamie Hayes이 [arXiv]에 게시한 ‘Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Scarcity

[논문리뷰] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

September 12, 2025

Zhaohui Yang이 [arXiv]에 게시한 ‘SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Dataset

[논문리뷰] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

September 12, 2025

Jian Gao이 [arXiv]에 게시한 ‘SpatialVID: A Large-Scale Video Dataset with Spatial Annotations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spatial Annotation

[논문리뷰] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

September 12, 2025

Jian Gao이 [arXiv]에 게시한 ‘SpatialVID: A Large-Scale Video Dataset with Spatial Annotations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Depth Map

[논문리뷰] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

September 12, 2025

Jian Gao이 [arXiv]에 게시한 ‘SpatialVID: A Large-Scale Video Dataset with Spatial Annotations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Structured Caption

[논문리뷰] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

September 12, 2025

Jian Gao이 [arXiv]에 게시한 ‘SpatialVID: A Large-Scale Video Dataset with Spatial Annotations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Motion Instruction

[논문리뷰] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

September 12, 2025

Jian Gao이 [arXiv]에 게시한 ‘SpatialVID: A Large-Scale Video Dataset with Spatial Annotations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

World Modeling

[논문리뷰] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

September 12, 2025

Jian Gao이 [arXiv]에 게시한 ‘SpatialVID: A Large-Scale Video Dataset with Spatial Annotations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Diversity Collapse

[논문리뷰] The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward

September 12, 2025

Xiaoyu Tan이 [arXiv]에 게시한 ‘The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward’ 논문에 대한...

Back to Top ↑

f-divergence

[논문리뷰] The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward

September 12, 2025

Xiaoyu Tan이 [arXiv]에 게시한 ‘The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward’ 논문에 대한...

Back to Top ↑

Forward-KL

[논문리뷰] The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward

September 12, 2025

Xiaoyu Tan이 [arXiv]에 게시한 ‘The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward’ 논문에 대한...

Back to Top ↑

JS-divergence

[논문리뷰] The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward

September 12, 2025

Xiaoyu Tan이 [arXiv]에 게시한 ‘The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward’ 논문에 대한...

Back to Top ↑

Model Adaptation

[논문리뷰] VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

September 12, 2025

Zirui Ge이 [arXiv]에 게시한 ‘VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bridge Attention

[논문리뷰] VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

September 12, 2025

Zirui Ge이 [arXiv]에 게시한 ‘VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Low-resource Training

[논문리뷰] VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

September 12, 2025

Zirui Ge이 [arXiv]에 게시한 ‘VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Programmability

[논문리뷰] Visual Programmability: A Guide for Code-as-Thought in Chart Understanding

September 12, 2025

Ethan Chern이 [arXiv]에 게시한 ‘Visual Programmability: A Guide for Code-as-Thought in Chart Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Code-as-Thought (CaT)

[논문리뷰] Visual Programmability: A Guide for Code-as-Thought in Chart Understanding

September 12, 2025

Ethan Chern이 [arXiv]에 게시한 ‘Visual Programmability: A Guide for Code-as-Thought in Chart Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Chart Understanding

[논문리뷰] Visual Programmability: A Guide for Code-as-Thought in Chart Understanding

September 12, 2025

Ethan Chern이 [arXiv]에 게시한 ‘Visual Programmability: A Guide for Code-as-Thought in Chart Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dual-Reward System

[논문리뷰] Visual Programmability: A Guide for Code-as-Thought in Chart Understanding

September 12, 2025

Ethan Chern이 [arXiv]에 게시한 ‘Visual Programmability: A Guide for Code-as-Thought in Chart Understanding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Headline Generation

[논문리뷰] CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China

September 15, 2025

XU Han이 [arXiv]에 게시한 ‘CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Minority Languages

[논문리뷰] CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China

September 15, 2025

XU Han이 [arXiv]에 게시한 ‘CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Low-Resource NLP

[논문리뷰] CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China

September 15, 2025

XU Han이 [arXiv]에 게시한 ‘CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Natural Language Generation

[논문리뷰] CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China

September 15, 2025

XU Han이 [arXiv]에 게시한 ‘CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Chinese Minority Languages

[논문리뷰] CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China

September 15, 2025

XU Han이 [arXiv]에 게시한 ‘CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Generalist Robot Policies

[논문리뷰] FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies

September 15, 2025

Fabian Otto이 [arXiv]에 게시한 ‘FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Intermediate Fusion

[논문리뷰] FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies

September 15, 2025

Fabian Otto이 [arXiv]에 게시한 ‘FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Noise Resistance

[논문리뷰] HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering

September 15, 2025

Zhehao Tan이 [arXiv]에 게시한 ‘HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Query Decomposition

[논문리뷰] HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering

September 15, 2025

Zhehao Tan이 [arXiv]에 게시한 ‘HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adaptive Retrieval

[논문리뷰] HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering

September 15, 2025

Zhehao Tan이 [arXiv]에 게시한 ‘HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Heuristic Framework

[논문리뷰] HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering

September 15, 2025

Zhehao Tan이 [arXiv]에 게시한 ‘HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Revelator

[논문리뷰] HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering

September 15, 2025

Zhehao Tan이 [arXiv]에 게시한 ‘HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Resolution-Agnostic

[논문리뷰] InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis

September 15, 2025

Song Guo이 [arXiv]에 게시한 ‘InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

VAE Decoder

[논문리뷰] InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis

September 15, 2025

Song Guo이 [arXiv]에 게시한 ‘InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

High-Resolution Image Generation

[논문리뷰] InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis

September 15, 2025

Song Guo이 [arXiv]에 게시한 ‘InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Inpainting

[논문리뷰] Inpainting-Guided Policy Optimization for Diffusion Large Language Models

September 15, 2025

Chenyu Wang이 [arXiv]에 게시한 ‘Inpainting-Guided Policy Optimization for Diffusion Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Educational Dialogue

[논문리뷰] IntrEx: A Dataset for Modeling Engagement in Educational Conversations

September 15, 2025

Gabriele Pergola이 [arXiv]에 게시한 ‘IntrEx: A Dataset for Modeling Engagement in Educational Conversations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Engagement Modeling

[논문리뷰] IntrEx: A Dataset for Modeling Engagement in Educational Conversations

September 15, 2025

Gabriele Pergola이 [arXiv]에 게시한 ‘IntrEx: A Dataset for Modeling Engagement in Educational Conversations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Second Language Learning

[논문리뷰] IntrEx: A Dataset for Modeling Engagement in Educational Conversations

September 15, 2025

Gabriele Pergola이 [arXiv]에 게시한 ‘IntrEx: A Dataset for Modeling Engagement in Educational Conversations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Readability Metrics

[논문리뷰] IntrEx: A Dataset for Modeling Engagement in Educational Conversations

September 15, 2025

Gabriele Pergola이 [arXiv]에 게시한 ‘IntrEx: A Dataset for Modeling Engagement in Educational Conversations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long-tailed Learning

[논문리뷰] LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios

September 15, 2025

Bing Su이 [arXiv]에 게시한 ‘LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semi-Supervised Learning

[논문리뷰] LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios

September 15, 2025

Bing Su이 [arXiv]에 게시한 ‘LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Open-World Scenarios

[논문리뷰] LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios

September 15, 2025

Bing Su이 [arXiv]에 게시한 ‘LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

OOD Detection

[논문리뷰] LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios

September 15, 2025

Bing Su이 [arXiv]에 게시한 ‘LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Confidence Calibration

[논문리뷰] LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios

September 15, 2025

Bing Su이 [arXiv]에 게시한 ‘LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Language Agents

[논문리뷰] MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools

September 15, 2025

Xiaorui Wang이 [arXiv]에 게시한 ‘MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-World Performance

[논문리뷰] MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools

September 15, 2025

Xiaorui Wang이 [arXiv]에 게시한 ‘MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

High-Frequency Trading

[논문리뷰] QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading

September 15, 2025

Chenyu You이 [arXiv]에 게시한 ‘QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Technical Analysis

[논문리뷰] QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading

September 15, 2025

Chenyu You이 [arXiv]에 게시한 ‘QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Algorithmic Trading

[논문리뷰] QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading

September 15, 2025

Chenyu You이 [arXiv]에 게시한 ‘QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Price-Driven Signals

[논문리뷰] QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading

September 15, 2025

Chenyu You이 [arXiv]에 게시한 ‘QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Execution Capability

[논문리뷰] The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs

September 15, 2025

Jonas Geiping이 [arXiv]에 게시한 ‘The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Conditioning

[논문리뷰] The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs

September 15, 2025

Jonas Geiping이 [arXiv]에 게시한 ‘The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Thinking Models

[논문리뷰] The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs

September 15, 2025

Jonas Geiping이 [arXiv]에 게시한 ‘The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Voice Style Adaptation

[논문리뷰] VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions

September 15, 2025

Dong Zhang이 [arXiv]에 게시한 ‘VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spoken Language Models

[논문리뷰] VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions

September 15, 2025

Dong Zhang이 [arXiv]에 게시한 ‘VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LALM-as-a-Judge

[논문리뷰] VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions

September 15, 2025

Dong Zhang이 [arXiv]에 게시한 ‘VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Speech Generation

[논문리뷰] VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions

September 15, 2025

Dong Zhang이 [arXiv]에 게시한 ‘VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Virtual Economy

[논문리뷰] Virtual Agent Economies

September 15, 2025

William A. Cunningham이 [arXiv]에 게시한 ‘Virtual Agent Economies’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Economic Mechanisms

[논문리뷰] Virtual Agent Economies

September 15, 2025

William A. Cunningham이 [arXiv]에 게시한 ‘Virtual Agent Economies’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Governance

[논문리뷰] Virtual Agent Economies

September 15, 2025

William A. Cunningham이 [arXiv]에 게시한 ‘Virtual Agent Economies’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Blockchain

[논문리뷰] Virtual Agent Economies

September 15, 2025

William A. Cunningham이 [arXiv]에 게시한 ‘Virtual Agent Economies’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agent Alignment

[논문리뷰] Virtual Agent Economies

September 15, 2025

William A. Cunningham이 [arXiv]에 게시한 ‘Virtual Agent Economies’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Shape Decomposition

[논문리뷰] X-Part: high fidelity and structure coherent shape decomposition

September 15, 2025

Yunhan Yang이 [arXiv]에 게시한 ‘X-Part: high fidelity and structure coherent shape decomposition’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Part-level Generation

[논문리뷰] X-Part: high fidelity and structure coherent shape decomposition

September 15, 2025

Yunhan Yang이 [arXiv]에 게시한 ‘X-Part: high fidelity and structure coherent shape decomposition’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bounding Box Prompts

[논문리뷰] X-Part: high fidelity and structure coherent shape decomposition

September 15, 2025

Yunhan Yang이 [arXiv]에 게시한 ‘X-Part: high fidelity and structure coherent shape decomposition’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sentiment Analysis

[논문리뷰] CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media

September 16, 2025

Subasish Das이 [arXiv]에 게시한 ‘CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Narrative Analysis

[논문리뷰] CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media

September 16, 2025

Subasish Das이 [arXiv]에 게시한 ‘CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Decentralized Social Media

[논문리뷰] CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media

September 16, 2025

Subasish Das이 [arXiv]에 게시한 ‘CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bluesky

[논문리뷰] CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media

September 16, 2025

Subasish Das이 [arXiv]에 게시한 ‘CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Topic Modeling

[논문리뷰] CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media

September 16, 2025

Subasish Das이 [arXiv]에 게시한 ‘CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-time Processing

[논문리뷰] CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media

September 16, 2025

Subasish Das이 [arXiv]에 게시한 ‘CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Hallucination

[논문리뷰] Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding

September 16, 2025

Li Zheng이 [arXiv]에 게시한 ‘Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Groundi...

Back to Top ↑

Large Video Models (LVMs)

[논문리뷰] Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding

September 16, 2025

Li Zheng이 [arXiv]에 게시한 ‘Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Groundi...

Back to Top ↑

Hierarchical Reasoning

[논문리뷰] Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding

September 16, 2025

Li Zheng이 [arXiv]에 게시한 ‘Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Groundi...

Back to Top ↑

Spatial-Temporal Grounding

[논문리뷰] Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding

September 16, 2025

Li Zheng이 [arXiv]에 게시한 ‘Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Groundi...

Back to Top ↑

Diagnostic Framework

[논문리뷰] Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding

September 16, 2025

Li Zheng이 [arXiv]에 게시한 ‘Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Groundi...

Back to Top ↑

Ethical Reasoning

[논문리뷰] EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI

September 16, 2025

UVSKKR이 [arXiv]에 게시한 ‘EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Mental Health AI

[논문리뷰] EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI

September 16, 2025

UVSKKR이 [arXiv]에 게시한 ‘EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human-in-the-loop

[논문리뷰] EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI

September 16, 2025

UVSKKR이 [arXiv]에 게시한 ‘EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Embedding Models

[논문리뷰] GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings

September 16, 2025

Yixuan Tang이 [arXiv]에 게시한 ‘GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gradient Alignment

[논문리뷰] GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings

September 16, 2025

Yixuan Tang이 [arXiv]에 게시한 ‘GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Fisher Information

[논문리뷰] GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings

September 16, 2025

Yixuan Tang이 [arXiv]에 게시한 ‘GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Scene Dataset

[논문리뷰] InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts

September 16, 2025

Wenzhe Cai이 [arXiv]에 게시한 ‘InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Simulation Environment

[논문리뷰] InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts

September 16, 2025

Wenzhe Cai이 [arXiv]에 게시한 ‘InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scene Generation

[논문리뷰] InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts

September 16, 2025

Wenzhe Cai이 [arXiv]에 게시한 ‘InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Point-Goal Navigation

[논문리뷰] InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts

September 16, 2025

Wenzhe Cai이 [arXiv]에 게시한 ‘InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Realistic Layouts

[논문리뷰] InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts

September 16, 2025

Wenzhe Cai이 [arXiv]에 게시한 ‘InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Object Interaction

[논문리뷰] InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts

September 16, 2025

Wenzhe Cai이 [arXiv]에 게시한 ‘InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-to-Sim

[논문리뷰] InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts

September 16, 2025

Wenzhe Cai이 [arXiv]에 게시한 ‘InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Modal Transformers

[논문리뷰] LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence

September 16, 2025

Lionel M. Ni이 [arXiv]에 게시한 ‘LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Drag-based Editing

[논문리뷰] LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence

September 16, 2025

Lionel M. Ni이 [arXiv]에 게시한 ‘LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Explicit Correspondence

[논문리뷰] LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence

September 16, 2025

Lionel M. Ni이 [arXiv]에 게시한 ‘LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-objective Reinforcement Learning

[논문리뷰] Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting

September 16, 2025

Changlong Yu이 [arXiv]에 게시한 ‘Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dynamic Reward Weighting

[논문리뷰] Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting

September 16, 2025

Changlong Yu이 [arXiv]에 게시한 ‘Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Pareto Front Optimization

[논문리뷰] Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting

September 16, 2025

Changlong Yu이 [arXiv]에 게시한 ‘Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hypervolume Indicator

[논문리뷰] Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting

September 16, 2025

Changlong Yu이 [arXiv]에 게시한 ‘Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gradient-based Optimization

[논문리뷰] Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting

September 16, 2025

Changlong Yu이 [arXiv]에 게시한 ‘Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Locality

[논문리뷰] Locality in Image Diffusion Models Emerges from Data Statistics

September 16, 2025

Vincent Sitzmann이 [arXiv]에 게시한 ‘Locality in Image Diffusion Models Emerges from Data Statistics’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Statistics

[논문리뷰] Locality in Image Diffusion Models Emerges from Data Statistics

September 16, 2025

Vincent Sitzmann이 [arXiv]에 게시한 ‘Locality in Image Diffusion Models Emerges from Data Statistics’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Optimal Denoiser

[논문리뷰] Locality in Image Diffusion Models Emerges from Data Statistics

September 16, 2025

Vincent Sitzmann이 [arXiv]에 게시한 ‘Locality in Image Diffusion Models Emerges from Data Statistics’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Wiener Filter

[논문리뷰] Locality in Image Diffusion Models Emerges from Data Statistics

September 16, 2025

Vincent Sitzmann이 [arXiv]에 게시한 ‘Locality in Image Diffusion Models Emerges from Data Statistics’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sensitivity Fields

[논문리뷰] Locality in Image Diffusion Models Emerges from Data Statistics

September 16, 2025

Vincent Sitzmann이 [arXiv]에 게시한 ‘Locality in Image Diffusion Models Emerges from Data Statistics’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Inductive Bias

[논문리뷰] Locality in Image Diffusion Models Emerges from Data Statistics

September 16, 2025

Vincent Sitzmann이 [arXiv]에 게시한 ‘Locality in Image Diffusion Models Emerges from Data Statistics’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reflection

[논문리뷰] Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models

September 16, 2025

Shuo Ren이 [arXiv]에 게시한 ‘Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Attention

[논문리뷰] Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models

September 16, 2025

Shuo Ren이 [arXiv]에 게시한 ‘Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Information Loss

[논문리뷰] Lost in Embeddings: Information Loss in Vision-Language Models

September 16, 2025

Ivan Vulić이 [arXiv]에 게시한 ‘Lost in Embeddings: Information Loss in Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Embeddings

[논문리뷰] Lost in Embeddings: Information Loss in Vision-Language Models

September 16, 2025

Ivan Vulić이 [arXiv]에 게시한 ‘Lost in Embeddings: Information Loss in Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Connectors

[논문리뷰] Lost in Embeddings: Information Loss in Vision-Language Models

September 16, 2025

Ivan Vulić이 [arXiv]에 게시한 ‘Lost in Embeddings: Information Loss in Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

k-NN Overlap Ratio

[논문리뷰] Lost in Embeddings: Information Loss in Vision-Language Models

September 16, 2025

Ivan Vulić이 [arXiv]에 게시한 ‘Lost in Embeddings: Information Loss in Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Embedding Reconstruction

[논문리뷰] Lost in Embeddings: Information Loss in Vision-Language Models

September 16, 2025

Ivan Vulić이 [arXiv]에 게시한 ‘Lost in Embeddings: Information Loss in Vision-Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Epistemic Humility

[논문리뷰] Measuring Epistemic Humility in Multimodal Large Language Models

September 16, 2025

Kaiyang Zhou이 [arXiv]에 게시한 ‘Measuring Epistemic Humility in Multimodal Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

False-Option Rejection

[논문리뷰] Measuring Epistemic Humility in Multimodal Large Language Models

September 16, 2025

Kaiyang Zhou이 [arXiv]에 게시한 ‘Measuring Epistemic Humility in Multimodal Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scene Graph

[논문리뷰] Measuring Epistemic Humility in Multimodal Large Language Models

September 16, 2025

Kaiyang Zhou이 [arXiv]에 게시한 ‘Measuring Epistemic Humility in Multimodal Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Modal Dataset

[논문리뷰] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

September 16, 2025

Yang Zhou이 [arXiv]에 게시한 ‘OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-Domain Data

[논문리뷰] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

September 16, 2025

Yang Zhou이 [arXiv]에 게시한 ‘OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Geometric Foundation Models

[논문리뷰] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

September 16, 2025

Yang Zhou이 [arXiv]에 게시한 ‘OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spatio-Temporal Data

[논문리뷰] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

September 16, 2025

Yang Zhou이 [arXiv]에 게시한 ‘OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dataset Benchmark

[논문리뷰] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

September 16, 2025

Yang Zhou이 [arXiv]에 게시한 ‘OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Dataset

[논문리뷰] PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits

September 16, 2025

Zhenhao Chen이 [arXiv]에 게시한 ‘PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Behavioral Traits

[논문리뷰] PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits

September 16, 2025

Zhenhao Chen이 [arXiv]에 게시한 ‘PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Causal Representation Learning

[논문리뷰] PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits

September 16, 2025

Zhenhao Chen이 [arXiv]에 게시한 ‘PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Big Five

[논문리뷰] PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits

September 16, 2025

Zhenhao Chen이 [arXiv]에 게시한 ‘PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Causal Discovery

[논문리뷰] PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits

September 16, 2025

Zhenhao Chen이 [arXiv]에 게시한 ‘PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semi-online RL

[논문리뷰] UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning

September 16, 2025

Yongliang Shen이 [arXiv]에 게시한 ‘UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Offline RL

[논문리뷰] UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning

September 16, 2025

Yongliang Shen이 [arXiv]에 게시한 ‘UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Patch Module

[논문리뷰] UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning

September 16, 2025

Yongliang Shen이 [arXiv]에 게시한 ‘UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Region Prompting

[논문리뷰] 3D Aware Region Prompted Vision Language Model

September 17, 2025

Xiaolong Li이 [arXiv]에 게시한 ‘3D Aware Region Prompted Vision Language Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Unified Representation

[논문리뷰] 3D Aware Region Prompted Vision Language Model

September 17, 2025

Xiaolong Li이 [arXiv]에 게시한 ‘3D Aware Region Prompted Vision Language Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Efficiency Optimization

[논문리뷰] EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving

September 17, 2025

Shansan Gong이 [arXiv]에 게시한 ‘EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Token Cost

[논문리뷰] EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving

September 17, 2025

Shansan Gong이 [arXiv]에 게시한 ‘EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sampling Cost

[논문리뷰] EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving

September 17, 2025

Shansan Gong이 [arXiv]에 게시한 ‘EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dynamic CoT Switching

[논문리뷰] EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving

September 17, 2025

Shansan Gong이 [arXiv]에 게시한 ‘EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Quantum Algorithms

[논문리뷰] Exact Coset Sampling for Quantum Lattice Algorithms

September 17, 2025

Yifan Zhang이 [arXiv]에 게시한 ‘Exact Coset Sampling for Quantum Lattice Algorithms’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Lattice Problems

[논문리뷰] Exact Coset Sampling for Quantum Lattice Algorithms

September 17, 2025

Yifan Zhang이 [arXiv]에 게시한 ‘Exact Coset Sampling for Quantum Lattice Algorithms’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Coset Sampling

[논문리뷰] Exact Coset Sampling for Quantum Lattice Algorithms

September 17, 2025

Yifan Zhang이 [arXiv]에 게시한 ‘Exact Coset Sampling for Quantum Lattice Algorithms’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Quantum Fourier Transform (QFT)

[논문리뷰] Exact Coset Sampling for Quantum Lattice Algorithms

September 17, 2025

Yifan Zhang이 [arXiv]에 게시한 ‘Exact Coset Sampling for Quantum Lattice Algorithms’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Modular Arithmetic

[논문리뷰] Exact Coset Sampling for Quantum Lattice Algorithms

September 17, 2025

Yifan Zhang이 [arXiv]에 게시한 ‘Exact Coset Sampling for Quantum Lattice Algorithms’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Quantum Cryptography

[논문리뷰] Exact Coset Sampling for Quantum Lattice Algorithms

September 17, 2025

Yifan Zhang이 [arXiv]에 게시한 ‘Exact Coset Sampling for Quantum Lattice Algorithms’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Exact Sampling

[논문리뷰] Exact Coset Sampling for Quantum Lattice Algorithms

September 17, 2025

Yifan Zhang이 [arXiv]에 게시한 ‘Exact Coset Sampling for Quantum Lattice Algorithms’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D Asset Generation

[논문리뷰] Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation

September 17, 2025

Lixin Xu이 [arXiv]에 게시한 ‘Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AI Pipeline

[논문리뷰] Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation

September 17, 2025

Lixin Xu이 [arXiv]에 게시한 ‘Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Game Development

[논문리뷰] Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation

September 17, 2025

Lixin Xu이 [arXiv]에 게시한 ‘Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Neural Modules

[논문리뷰] Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation

September 17, 2025

Lixin Xu이 [arXiv]에 게시한 ‘Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Retopology

[논문리뷰] Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation

September 17, 2025

Lixin Xu이 [arXiv]에 게시한 ‘Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

UV Unwrapping

[논문리뷰] Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation

September 17, 2025

Lixin Xu이 [arXiv]에 게시한 ‘Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Science AI

[논문리뷰] Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge

September 17, 2025

Wentao Zhang이 [arXiv]에 게시한 ‘Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Caption-assisted Reasoning

[논문리뷰] Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge

September 17, 2025

Wentao Zhang이 [arXiv]에 게시한 ‘Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

SeePhys Challenge

[논문리뷰] Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge

September 17, 2025

Wentao Zhang이 [arXiv]에 게시한 ‘Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Physics Problems

[논문리뷰] Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge

September 17, 2025

Wentao Zhang이 [arXiv]에 게시한 ‘Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-modal Alignment

[논문리뷰] Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge

September 17, 2025

Wentao Zhang이 [arXiv]에 게시한 ‘Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multiple Instance Learning

[논문리뷰] Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis

September 17, 2025

Bo Liu이 [arXiv]에 게시한 ‘Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hard Instance Mining

[논문리뷰] Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis

September 17, 2025

Bo Liu이 [arXiv]에 게시한 ‘Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Computational Pathology

[논문리뷰] Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis

September 17, 2025

Bo Liu이 [arXiv]에 게시한 ‘Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Whole Slide Images

[논문리뷰] Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis

September 17, 2025

Bo Liu이 [arXiv]에 게시한 ‘Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Masked Learning

[논문리뷰] Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis

September 17, 2025

Bo Liu이 [arXiv]에 게시한 ‘Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Siamese Network

[논문리뷰] Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis

September 17, 2025

Bo Liu이 [arXiv]에 게시한 ‘Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Medical Image Analysis

[논문리뷰] Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis

September 17, 2025

Bo Liu이 [arXiv]에 게시한 ‘Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Post-training Quantization

[논문리뷰] Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs

September 17, 2025

Luca Benini이 [arXiv]에 게시한 ‘Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hessian-based Optimization

[논문리뷰] Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs

September 17, 2025

Luca Benini이 [arXiv]에 게시한 ‘Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Error Compensation

[논문리뷰] Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs

September 17, 2025

Luca Benini이 [arXiv]에 게시한 ‘Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Low-bit LLMs

[논문리뷰] Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs

September 17, 2025

Luca Benini이 [arXiv]에 게시한 ‘Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Summarization

[논문리뷰] ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization

September 17, 2025

Litu Ou이 [arXiv]에 게시한 ‘ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

ReAct

[논문리뷰] ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization

September 17, 2025

Litu Ou이 [arXiv]에 게시한 ‘ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agentic LLMs

[논문리뷰] Scaling Agents via Continual Pre-training

September 17, 2025

Guangyu Li이 [arXiv]에 게시한 ‘Scaling Agents via Continual Pre-training’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Continual Pre-training

[논문리뷰] Scaling Agents via Continual Pre-training

September 17, 2025

Guangyu Li이 [arXiv]에 게시한 ‘Scaling Agents via Continual Pre-training’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-step Reasoning

[논문리뷰] Scaling Agents via Continual Pre-training

September 17, 2025

Guangyu Li이 [arXiv]에 게시한 ‘Scaling Agents via Continual Pre-training’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Variance Reduction

[논문리뷰] Single-stream Policy Optimization

September 17, 2025

Zihan Ding이 [arXiv]에 게시한 ‘Single-stream Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Environment Scaling

[논문리뷰] Towards General Agentic Intelligence via Environment Scaling

September 17, 2025

Guangyu Li이 [arXiv]에 게시한 ‘Towards General Agentic Intelligence via Environment Scaling’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Tool-Augmented LLMs

[논문리뷰] WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents

September 17, 2025

Wenbiao Yin이 [arXiv]에 게시한 ‘WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Knowledge Graphs

[논문리뷰] WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning

September 17, 2025

Huifeng Yin이 [arXiv]에 게시한 ‘WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Open-Ended Deep Research

[논문리뷰] WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research

September 17, 2025

Houquan Zhou이 [arXiv]에 게시한 ‘WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dynamic Outline

[논문리뷰] WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research

September 17, 2025

Houquan Zhou이 [arXiv]에 게시한 ‘WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Evidence Acquisition

[논문리뷰] WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research

September 17, 2025

Houquan Zhou이 [arXiv]에 게시한 ‘WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hierarchical Writing

[논문리뷰] WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research

September 17, 2025

Houquan Zhou이 [arXiv]에 게시한 ‘WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Memory Bank

[논문리뷰] WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research

September 17, 2025

Houquan Zhou이 [arXiv]에 게시한 ‘WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multidisciplinary

[논문리뷰] GenExam: A Multidisciplinary Text-to-Image Exam

September 18, 2025

Yu Qiao이 [arXiv]에 게시한 ‘GenExam: A Multidisciplinary Text-to-Image Exam’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scoring System

[논문리뷰] GenExam: A Multidisciplinary Text-to-Image Exam

September 18, 2025

Yu Qiao이 [arXiv]에 게시한 ‘GenExam: A Multidisciplinary Text-to-Image Exam’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

FP8 Quantization

[논문리뷰] Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale

September 18, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Bootstrapping

[논문리뷰] Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale

September 18, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Language-Centric AI

[논문리뷰] Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale

September 18, 2025

Bernard Ghanem이 [arXiv]에 게시한 ‘Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Context Fidelity

[논문리뷰] Improving Context Fidelity via Native Retrieval-Augmented Reasoning

September 18, 2025

Xiangru Tang이 [arXiv]에 게시한 ‘Improving Context Fidelity via Native Retrieval-Augmented Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Retrieval-Augmented Generation (RAG)

[논문리뷰] Improving Context Fidelity via Native Retrieval-Augmented Reasoning

September 18, 2025

Xiangru Tang이 [arXiv]에 게시한 ‘Improving Context Fidelity via Native Retrieval-Augmented Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

In-context Retrieval

[논문리뷰] Improving Context Fidelity via Native Retrieval-Augmented Reasoning

September 18, 2025

Xiangru Tang이 [arXiv]에 게시한 ‘Improving Context Fidelity via Native Retrieval-Augmented Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Advertisement Video Analysis

[논문리뷰] MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook

September 18, 2025

Bowen Zhou이 [arXiv]에 게시한 ‘MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-world Scenarios

[논문리뷰] MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook

September 18, 2025

Bowen Zhou이 [arXiv]에 게시한 ‘MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Challenge Benchmark

[논문리뷰] MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook

September 18, 2025

Bowen Zhou이 [arXiv]에 게시한 ‘MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Omnidirectional Vision

[논문리뷰] PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era

September 18, 2025

Zihao Dongfang이 [arXiv]에 게시한 ‘PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Panoramic Perception

[논문리뷰] PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era

September 18, 2025

Zihao Dongfang이 [arXiv]에 게시한 ‘PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dataset Development

[논문리뷰] PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era

September 18, 2025

Zihao Dongfang이 [arXiv]에 게시한 ‘PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Robot Navigation

[논문리뷰] PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era

September 18, 2025

Zihao Dongfang이 [arXiv]에 게시한 ‘PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

System Architecture

[논문리뷰] PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era

September 18, 2025

Zihao Dongfang이 [arXiv]에 게시한 ‘PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

SAIL-ViT

[논문리뷰] SAIL-VL2 Technical Report

September 18, 2025

Zijian Kang이 [arXiv]에 게시한 ‘SAIL-VL2 Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Code Language Models

[논문리뷰] Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning

September 18, 2025

Zhou Yang이 [arXiv]에 게시한 ‘Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sensitive Memorization

[논문리뷰] Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning

September 18, 2025

Zhou Yang이 [arXiv]에 게시한 ‘Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Privacy

[논문리뷰] Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning

September 18, 2025

Zhou Yang이 [arXiv]에 게시한 ‘Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gradient Ascent

[논문리뷰] Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning

September 18, 2025

Zhou Yang이 [arXiv]에 게시한 ‘Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Utility

[논문리뷰] Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning

September 18, 2025

Zhou Yang이 [arXiv]에 게시한 ‘Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Representation Steering

[논문리뷰] SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

September 18, 2025

Zhun Wang이 [arXiv]에 게시한 ‘SteeringControl: Holistic Evaluation of Alignment Steering in LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Behavioral Entanglement

[논문리뷰] SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

September 18, 2025

Zhun Wang이 [arXiv]에 게시한 ‘SteeringControl: Holistic Evaluation of Alignment Steering in LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Harmful Generation

[논문리뷰] SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

September 18, 2025

Zhun Wang이 [arXiv]에 게시한 ‘SteeringControl: Holistic Evaluation of Alignment Steering in LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hallucination Control

[논문리뷰] SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

September 18, 2025

Zhun Wang이 [arXiv]에 게시한 ‘SteeringControl: Holistic Evaluation of Alignment Steering in LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Modular Framework

[논문리뷰] SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

September 18, 2025

Zhun Wang이 [arXiv]에 게시한 ‘SteeringControl: Holistic Evaluation of Alignment Steering in LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hierarchical Optimization

[논문리뷰] THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning

September 18, 2025

Yicheng Pan이 [arXiv]에 게시한 ‘THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Character Animation

[논문리뷰] Wan-Animate: Unified Character Animation and Replacement with Holistic Replication

September 18, 2025

Mingyang Huang이 [arXiv]에 게시한 ‘Wan-Animate: Unified Character Animation and Replacement with Holistic Replication’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Replacement

[논문리뷰] Wan-Animate: Unified Character Animation and Replacement with Holistic Replication

September 18, 2025

Mingyang Huang이 [arXiv]에 게시한 ‘Wan-Animate: Unified Character Animation and Replacement with Holistic Replication’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Relighting LoRA

[논문리뷰] Wan-Animate: Unified Character Animation and Replacement with Holistic Replication

September 18, 2025

Mingyang Huang이 [arXiv]에 게시한 ‘Wan-Animate: Unified Character Animation and Replacement with Holistic Replication’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Holistic Replication

[논문리뷰] Wan-Animate: Unified Character Animation and Replacement with Holistic Replication

September 18, 2025

Mingyang Huang이 [arXiv]에 게시한 ‘Wan-Animate: Unified Character Animation and Replacement with Holistic Replication’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Unified Visual Tokenizer

[논문리뷰] AToken: A Unified Tokenizer for Vision

September 19, 2025

Mingze Xu이 [arXiv]에 게시한 ‘AToken: A Unified Tokenizer for Vision’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

4D Representation

[논문리뷰] AToken: A Unified Tokenizer for Vision

September 19, 2025

Mingze Xu이 [arXiv]에 게시한 ‘AToken: A Unified Tokenizer for Vision’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adversarial-free Training

[논문리뷰] AToken: A Unified Tokenizer for Vision

September 19, 2025

Mingze Xu이 [arXiv]에 게시한 ‘AToken: A Unified Tokenizer for Vision’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reconstruction

[논문리뷰] AToken: A Unified Tokenizer for Vision

September 19, 2025

Mingze Xu이 [arXiv]에 게시한 ‘AToken: A Unified Tokenizer for Vision’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semantic Understanding

[논문리뷰] AToken: A Unified Tokenizer for Vision

September 19, 2025

Mingze Xu이 [arXiv]에 게시한 ‘AToken: A Unified Tokenizer for Vision’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Ultrasound Imaging

[논문리뷰] EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence

September 19, 2025

Qinghua Huang이 [arXiv]에 게시한 ‘EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Label-free Reinforcement Learning

[논문리뷰] Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation

September 19, 2025

Kishan Panaganti이 [arXiv]에 게시한 ‘Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-improvement

[논문리뷰] Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation

September 19, 2025

Kishan Panaganti이 [arXiv]에 게시한 ‘Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Entropy Collapse

[논문리뷰] Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation

September 19, 2025

Kishan Panaganti이 [arXiv]에 게시한 ‘Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Novelty Reward

[논문리뷰] Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation

September 19, 2025

Kishan Panaganti이 [arXiv]에 게시한 ‘Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Test-Time RL

[논문리뷰] Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation

September 19, 2025

Kishan Panaganti이 [arXiv]에 게시한 ‘Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Evolutionary Computing Principles

[논문리뷰] Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation

September 19, 2025

Kishan Panaganti이 [arXiv]에 게시한 ‘Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Change Detection

[논문리뷰] FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection

September 19, 2025

Zhewei Zhang이 [arXiv]에 게시한 ‘FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Frequency-Spatial Analysis

[논문리뷰] FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection

September 19, 2025

Zhewei Zhang이 [arXiv]에 게시한 ‘FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Wavelet Transform

[논문리뷰] FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection

September 19, 2025

Zhewei Zhang이 [arXiv]에 게시한 ‘FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Gated Fusion

[논문리뷰] FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection

September 19, 2025

Zhewei Zhang이 [arXiv]에 게시한 ‘FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agent Benchmarking

[논문리뷰] FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning

September 19, 2025

Jiashuo Liu이 [arXiv]에 게시한 ‘FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Open-domain Search

[논문리뷰] FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning

September 19, 2025

Jiashuo Liu이 [arXiv]에 게시한 ‘FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Time-Sensitive Data

[논문리뷰] FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning

September 19, 2025

Jiashuo Liu이 [arXiv]에 게시한 ‘FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reward Distribution Matching

[논문리뷰] FlowRL: Matching Reward Distributions for LLM Reasoning

September 19, 2025

Hengli Li이 [arXiv]에 게시한 ‘FlowRL: Matching Reward Distributions for LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GFlowNets

[논문리뷰] FlowRL: Matching Reward Distributions for LLM Reasoning

September 19, 2025

Hengli Li이 [arXiv]에 게시한 ‘FlowRL: Matching Reward Distributions for LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Diverse Reasoning

[논문리뷰] FlowRL: Matching Reward Distributions for LLM Reasoning

September 19, 2025

Hengli Li이 [arXiv]에 게시한 ‘FlowRL: Matching Reward Distributions for LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Flow-Balanced Optimization

[논문리뷰] FlowRL: Matching Reward Distributions for LLM Reasoning

September 19, 2025

Hengli Li이 [arXiv]에 게시한 ‘FlowRL: Matching Reward Distributions for LLM Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multiple-Choice QA

[논문리뷰] Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs

September 19, 2025

Katharina von der Wense이 [arXiv]에 게시한 ‘Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Tokenization

[논문리뷰] Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs

September 19, 2025

Katharina von der Wense이 [arXiv]에 게시한 ‘Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Accuracy

[논문리뷰] Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs

September 19, 2025

Katharina von der Wense이 [arXiv]에 게시한 ‘Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Ranking

[논문리뷰] Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs

September 19, 2025

Katharina von der Wense이 [arXiv]에 게시한 ‘Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Instruction-based Image Editing

[논문리뷰] MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks

September 19, 2025

Xijun Gu이 [arXiv]에 게시한 ‘MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-modal LLM

[논문리뷰] MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks

September 19, 2025

Xijun Gu이 [arXiv]에 게시한 ‘MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Specification Alignment

[논문리뷰] Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration

September 19, 2025

Zhilin Wang이 [arXiv]에 게시한 ‘Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Test-Time Deliberation

[논문리뷰] Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration

September 19, 2025

Zhilin Wang이 [arXiv]에 게시한 ‘Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Safety-Behavior Trade-off

[논문리뷰] Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration

September 19, 2025

Zhilin Wang이 [arXiv]에 게시한 ‘Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

ALIGN3

[논문리뷰] Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration

September 19, 2025

Zhilin Wang이 [arXiv]에 게시한 ‘Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

SPECBENCH

[논문리뷰] Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration

September 19, 2025

Zhilin Wang이 [arXiv]에 게시한 ‘Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agentic Recommender Systems

[논문리뷰] RecoWorld: Building Simulated Environments for Agentic Recommender Systems

September 19, 2025

Mingyuan Wu이 [arXiv]에 게시한 ‘RecoWorld: Building Simulated Environments for Agentic Recommender Systems’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Simulated Environments

[논문리뷰] RecoWorld: Building Simulated Environments for Agentic Recommender Systems

September 19, 2025

Mingyuan Wu이 [arXiv]에 게시한 ‘RecoWorld: Building Simulated Environments for Agentic Recommender Systems’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LLM-driven Simulation

[논문리뷰] RecoWorld: Building Simulated Environments for Agentic Recommender Systems

September 19, 2025

Mingyuan Wu이 [arXiv]에 게시한 ‘RecoWorld: Building Simulated Environments for Agentic Recommender Systems’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

User Retention

[논문리뷰] RecoWorld: Building Simulated Environments for Agentic Recommender Systems

September 19, 2025

Mingyuan Wu이 [arXiv]에 게시한 ‘RecoWorld: Building Simulated Environments for Agentic Recommender Systems’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Vision-Language-Action (VLA) Model

[논문리뷰] RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

September 19, 2025

SpaceProduct이 [arXiv]에 게시한 ‘RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human Demonstrations

[논문리뷰] RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

September 19, 2025

SpaceProduct이 [arXiv]에 게시한 ‘RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Generative Pretraining

[논문리뷰] RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

September 19, 2025

SpaceProduct이 [arXiv]에 게시한 ‘RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Ego-Centric Video

[논문리뷰] RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

September 19, 2025

SpaceProduct이 [arXiv]에 게시한 ‘RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Trajectory Prediction

[논문리뷰] RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

September 19, 2025

SpaceProduct이 [arXiv]에 게시한 ‘RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

ActionVAE

[논문리뷰] RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

September 19, 2025

SpaceProduct이 [arXiv]에 게시한 ‘RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Computer Use Agents

[논문리뷰] ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

September 19, 2025

Zehao Li이 [arXiv]에 게시한 ‘ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-Platform Data

[논문리뷰] ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

September 19, 2025

Zehao Li이 [arXiv]에 게시한 ‘ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Scaling

[논문리뷰] ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

September 19, 2025

Zehao Li이 [arXiv]에 게시한 ‘ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Task Completion

[논문리뷰] ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

September 19, 2025

Zehao Li이 [arXiv]에 게시한 ‘ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Masked Image Modeling

[논문리뷰] Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation

September 19, 2025

Xihui Liu이 [arXiv]에 게시한 ‘Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LlamaGen

[논문리뷰] Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation

September 19, 2025

Xihui Liu이 [arXiv]에 게시한 ‘Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spatio-Temporal Video Grounding

[논문리뷰] Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding

September 19, 2025

Rynson W. H. Lau이 [arXiv]에 게시한 ‘Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Decomposed Spatio-Temporal Highlighting

[논문리뷰] Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding

September 19, 2025

Rynson W. H. Lau이 [arXiv]에 게시한 ‘Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Logit-Guided Re-attention

[논문리뷰] Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding

September 19, 2025

Rynson W. H. Lau이 [arXiv]에 게시한 ‘Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Temporal-Augmented Assembling

[논문리뷰] Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding

September 19, 2025

Rynson W. H. Lau이 [arXiv]에 게시한 ‘Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D/4D Generation

[논문리뷰] WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance

September 19, 2025

Ruibo Li이 [arXiv]에 게시한 ‘WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Training-Free Guidance

[논문리뷰] WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance

September 19, 2025

Ruibo Li이 [arXiv]에 게시한 ‘WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Camera Trajectory Control

[논문리뷰] WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance

September 19, 2025

Ruibo Li이 [arXiv]에 게시한 ‘WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Geometric Consistency

[논문리뷰] WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance

September 19, 2025

Ruibo Li이 [arXiv]에 게시한 ‘WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Inference-Time Optimization

[논문리뷰] WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance

September 19, 2025

Ruibo Li이 [arXiv]에 게시한 ‘WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dense Rewards

[논문리뷰] A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning

September 22, 2025

Jiangmiao이 [arXiv]에 게시한 ‘A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Low-level Actions

[논문리뷰] Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue

September 22, 2025

Hui Zhang이 [arXiv]에 게시한 ‘Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Human-GUI Interaction

[논문리뷰] BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent

September 22, 2025

Jiahui Yang이 [arXiv]에 게시한 ‘BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cognitive Modeling

[논문리뷰] BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent

September 22, 2025

Jiahui Yang이 [arXiv]에 게시한 ‘BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Reward Model

[논문리뷰] BaseReward: A Strong Baseline for Multimodal Reward Model

September 22, 2025

jianfeipan이 [arXiv]에 게시한 ‘BaseReward: A Strong Baseline for Multimodal Reward Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

MLLM Alignment

[논문리뷰] BaseReward: A Strong Baseline for Multimodal Reward Model

September 22, 2025

jianfeipan이 [arXiv]에 게시한 ‘BaseReward: A Strong Baseline for Multimodal Reward Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reward Head Architecture

[논문리뷰] BaseReward: A Strong Baseline for Multimodal Reward Model

September 22, 2025

jianfeipan이 [arXiv]에 게시한 ‘BaseReward: A Strong Baseline for Multimodal Reward Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Ensemble Methods

[논문리뷰] BaseReward: A Strong Baseline for Multimodal Reward Model

September 22, 2025

jianfeipan이 [arXiv]에 게시한 ‘BaseReward: A Strong Baseline for Multimodal Reward Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

BaseReward

[논문리뷰] BaseReward: A Strong Baseline for Multimodal Reward Model

September 22, 2025

jianfeipan이 [arXiv]에 게시한 ‘BaseReward: A Strong Baseline for Multimodal Reward Model’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Instruction-Guided TTS

[논문리뷰] Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems

September 22, 2025

Hung-yi Lee이 [arXiv]에 게시한 ‘Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems’ 논문에 대...

Back to Top ↑

Expressive Speech Synthesis

[논문리뷰] Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems

September 22, 2025

Hung-yi Lee이 [arXiv]에 게시한 ‘Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems’ 논문에 대...

Back to Top ↑

Subjective Evaluation

[논문리뷰] Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems

September 22, 2025

Hung-yi Lee이 [arXiv]에 게시한 ‘Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems’ 논문에 대...

Back to Top ↑

Controllability

[논문리뷰] Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems

September 22, 2025

Hung-yi Lee이 [arXiv]에 게시한 ‘Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems’ 논문에 대...

Back to Top ↑

Generative Modeling

[논문리뷰] Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

September 22, 2025

Wenyu Wang이 [arXiv]에 게시한 ‘Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Representation Learning

[논문리뷰] Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

September 22, 2025

Wenyu Wang이 [arXiv]에 게시한 ‘Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Classification

[논문리뷰] Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

September 22, 2025

Wenyu Wang이 [arXiv]에 게시한 ‘Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Personalized Video Generation

[논문리뷰] Lynx: Towards High-Fidelity Personalized Video Generation

September 22, 2025

Linjie Luo이 [arXiv]에 게시한 ‘Lynx: Towards High-Fidelity Personalized Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adapter Networks

[논문리뷰] Lynx: Towards High-Fidelity Personalized Video Generation

September 22, 2025

Linjie Luo이 [arXiv]에 게시한 ‘Lynx: Towards High-Fidelity Personalized Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Facial Recognition

[논문리뷰] Lynx: Towards High-Fidelity Personalized Video Generation

September 22, 2025

Linjie Luo이 [arXiv]에 게시한 ‘Lynx: Towards High-Fidelity Personalized Video Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hybrid Tokenizer

[논문리뷰] MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

September 22, 2025

jialingt이 [arXiv]에 게시한 ‘MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Diffusion Decoder

[논문리뷰] MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

September 22, 2025

jialingt이 [arXiv]에 게시한 ‘MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Scaling

[논문리뷰] MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

September 22, 2025

jialingt이 [arXiv]에 게시한 ‘MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Camera Parameter Optimization

[논문리뷰] RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes

September 22, 2025

Narendra Ahuja이 [arXiv]에 게시한 ‘RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

RGB-Only Supervision

[논문리뷰] RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes

September 22, 2025

Narendra Ahuja이 [arXiv]에 게시한 ‘RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Structure from Motion

[논문리뷰] RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes

September 22, 2025

Narendra Ahuja이 [arXiv]에 게시한 ‘RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Outlier Robustness

[논문리뷰] RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes

September 22, 2025

Narendra Ahuja이 [arXiv]에 게시한 ‘RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Two-stage Optimization

[논문리뷰] RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes

September 22, 2025

Narendra Ahuja이 [arXiv]에 게시한 ‘RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Point Tracking

[논문리뷰] RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes

September 22, 2025

Narendra Ahuja이 [arXiv]에 게시한 ‘RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Repository Planning

[논문리뷰] RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation

September 22, 2025

Steven Liu이 [arXiv]에 게시한 ‘RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Graph-based Representation

[논문리뷰] RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation

September 22, 2025

Steven Liu이 [arXiv]에 게시한 ‘RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Scalable Codebase

[논문리뷰] RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation

September 22, 2025

Steven Liu이 [arXiv]에 게시한 ‘RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Layout Guidance

[논문리뷰] SPATIALGEN: Layout-guided 3D Indoor Scene Generation

September 22, 2025

Yongsen Mao이 [arXiv]에 게시한 ‘SPATIALGEN: Layout-guided 3D Indoor Scene Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Synthetic Dataset

[논문리뷰] SPATIALGEN: Layout-guided 3D Indoor Scene Generation

September 22, 2025

Yongsen Mao이 [arXiv]에 게시한 ‘SPATIALGEN: Layout-guided 3D Indoor Scene Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Indoor Environments

[논문리뷰] SPATIALGEN: Layout-guided 3D Indoor Scene Generation

September 22, 2025

Yongsen Mao이 [arXiv]에 게시한 ‘SPATIALGEN: Layout-guided 3D Indoor Scene Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Semantic Consistency

[논문리뷰] SPATIALGEN: Layout-guided 3D Indoor Scene Generation

September 22, 2025

Yongsen Mao이 [arXiv]에 게시한 ‘SPATIALGEN: Layout-guided 3D Indoor Scene Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Role-playing Agents (RPAs)

[논문리뷰] Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents

September 22, 2025

Chao Zhang이 [arXiv]에 게시한 ‘Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dynamic Role Profiles

[논문리뷰] Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents

September 22, 2025

Chao Zhang이 [arXiv]에 게시한 ‘Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adaptive Temporal Sampling

[논문리뷰] Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents

September 22, 2025

Chao Zhang이 [arXiv]에 게시한 ‘Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-Only Training

[논문리뷰] WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers

September 22, 2025

Karun Kumar이 [arXiv]에 게시한 ‘WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Deep Supervision

[논문리뷰] WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers

September 22, 2025

Karun Kumar이 [arXiv]에 게시한 ‘WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Whisper

[논문리뷰] WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers

September 22, 2025

Karun Kumar이 [arXiv]에 게시한 ‘WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Encoder-Decoder Models

[논문리뷰] WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers

September 22, 2025

Karun Kumar이 [arXiv]에 게시한 ‘WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agent Environments

[논문리뷰] ARE: Scaling Up Agent Environments and Evaluations

September 23, 2025

Matteo Bettini이 [arXiv]에 게시한 ‘ARE: Scaling Up Agent Environments and Evaluations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Asynchronous Systems

[논문리뷰] ARE: Scaling Up Agent Environments and Evaluations

September 23, 2025

Matteo Bettini이 [arXiv]에 게시한 ‘ARE: Scaling Up Agent Environments and Evaluations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-agent Collaboration

[논문리뷰] ARE: Scaling Up Agent Environments and Evaluations

September 23, 2025

Matteo Bettini이 [arXiv]에 게시한 ‘ARE: Scaling Up Agent Environments and Evaluations’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Model Knowledge

[논문리뷰] Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels

September 23, 2025

Qi Zhang이 [arXiv]에 게시한 ‘Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Closed-Book Question Answering (CBQA)

[논문리뷰] Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels

September 23, 2025

Qi Zhang이 [arXiv]에 게시한 ‘Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Parameter Restoration

[논문리뷰] Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels

September 23, 2025

Qi Zhang이 [arXiv]에 게시한 ‘Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Kullback-Leibler Divergence

[논문리뷰] Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels

September 23, 2025

Qi Zhang이 [arXiv]에 게시한 ‘Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Knowledge Forgetting

[논문리뷰] Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels

September 23, 2025

Qi Zhang이 [arXiv]에 게시한 ‘Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Auditory Knowledge

[논문리뷰] AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?

September 23, 2025

Jaeho Lee이 [arXiv]에 게시한 ‘AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Auditory Imagination

[논문리뷰] AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?

September 23, 2025

Jaeho Lee이 [arXiv]에 게시한 ‘AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Text-only Reasoning

[논문리뷰] AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?

September 23, 2025

Jaeho Lee이 [arXiv]에 게시한 ‘AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Parallel Manipulator

[논문리뷰] ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces

September 23, 2025

Jiafeng Xu이 [arXiv]에 게시한 ‘ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Robotic Wrist

[논문리뷰] ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces

September 23, 2025

Jiafeng Xu이 [arXiv]에 게시한 ‘ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Confined Space Manipulation

[논문리뷰] ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces

September 23, 2025

Jiafeng Xu이 [arXiv]에 게시한 ‘ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Kinematics

[논문리뷰] ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces

September 23, 2025

Jiafeng Xu이 [arXiv]에 게시한 ‘ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Anthropomorphic Robot

[논문리뷰] ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces

September 23, 2025

Jiafeng Xu이 [arXiv]에 게시한 ‘ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Robot Design

[논문리뷰] ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces

September 23, 2025

Jiafeng Xu이 [arXiv]에 게시한 ‘ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Code Review

[논문리뷰] CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects

September 23, 2025

Hang Yu이 [arXiv]에 게시한 ‘CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Python Projects

[논문리뷰] CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects

September 23, 2025

Hang Yu이 [arXiv]에 게시한 ‘CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

End-to-End Evaluation

[논문리뷰] CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects

September 23, 2025

Hang Yu이 [arXiv]에 게시한 ‘CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Object Editing

[논문리뷰] ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment

September 23, 2025

Yue Ma이 [arXiv]에 게시한 ‘ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adaptive Context Enrichment

[논문리뷰] ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment

September 23, 2025

Yue Ma이 [arXiv]에 게시한 ‘ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Guidance Responsiveness

[논문리뷰] ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment

September 23, 2025

Yue Ma이 [arXiv]에 게시한 ‘ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-attention

[논문리뷰] Cross-Attention is Half Explanation in Speech-to-Text Models

September 23, 2025

Luisa Bentivogli이 [arXiv]에 게시한 ‘Cross-Attention is Half Explanation in Speech-to-Text Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Speech-to-Text (S2T)

[논문리뷰] Cross-Attention is Half Explanation in Speech-to-Text Models

September 23, 2025

Luisa Bentivogli이 [arXiv]에 게시한 ‘Cross-Attention is Half Explanation in Speech-to-Text Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Saliency Maps

[논문리뷰] Cross-Attention is Half Explanation in Speech-to-Text Models

September 23, 2025

Luisa Bentivogli이 [arXiv]에 게시한 ‘Cross-Attention is Half Explanation in Speech-to-Text Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Feature Attribution

[논문리뷰] Cross-Attention is Half Explanation in Speech-to-Text Models

September 23, 2025

Luisa Bentivogli이 [arXiv]에 게시한 ‘Cross-Attention is Half Explanation in Speech-to-Text Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Context Mixing

[논문리뷰] Cross-Attention is Half Explanation in Speech-to-Text Models

September 23, 2025

Luisa Bentivogli이 [arXiv]에 게시한 ‘Cross-Attention is Half Explanation in Speech-to-Text Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Correlation

[논문리뷰] Cross-Attention is Half Explanation in Speech-to-Text Models

September 23, 2025

Luisa Bentivogli이 [arXiv]에 게시한 ‘Cross-Attention is Half Explanation in Speech-to-Text Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cultural Adaptation

[논문리뷰] DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultural Text Adaptation in Indian Context

September 23, 2025

Maunendra Sankar Desarkar이 [arXiv]에 게시한 ‘DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultur...

Back to Top ↑

Indian Culture

[논문리뷰] DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultural Text Adaptation in Indian Context

September 23, 2025

Maunendra Sankar Desarkar이 [arXiv]에 게시한 ‘DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultur...

Back to Top ↑

CSI

[논문리뷰] DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultural Text Adaptation in Indian Context

September 23, 2025

Maunendra Sankar Desarkar이 [arXiv]에 게시한 ‘DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultur...

Back to Top ↑

Cultural Bias

[논문리뷰] DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultural Text Adaptation in Indian Context

September 23, 2025

Maunendra Sankar Desarkar이 [arXiv]에 게시한 ‘DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultur...

Back to Top ↑

Forward Process

[논문리뷰] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

September 23, 2025

Qinsheng Zhang이 [arXiv]에 게시한 ‘DiffusionNFT: Online Diffusion Reinforcement with Forward Process’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

CFG-free

[논문리뷰] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

September 23, 2025

Qinsheng Zhang이 [arXiv]에 게시한 ‘DiffusionNFT: Online Diffusion Reinforcement with Forward Process’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Negative-Aware FineTuning

[논문리뷰] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

September 23, 2025

Qinsheng Zhang이 [arXiv]에 게시한 ‘DiffusionNFT: Online Diffusion Reinforcement with Forward Process’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

KV Cache Management

[논문리뷰] EpiCache: Episodic KV Cache Management for Long Conversational Question Answering

September 23, 2025

Minsik Cho이 [arXiv]에 게시한 ‘EpiCache: Episodic KV Cache Management for Long Conversational Question Answering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Long Conversational QA

[논문리뷰] EpiCache: Episodic KV Cache Management for Long Conversational Question Answering

September 23, 2025

Minsik Cho이 [arXiv]에 게시한 ‘EpiCache: Episodic KV Cache Management for Long Conversational Question Answering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Episodic Clustering

[논문리뷰] EpiCache: Episodic KV Cache Management for Long Conversational Question Answering

September 23, 2025

Minsik Cho이 [arXiv]에 게시한 ‘EpiCache: Episodic KV Cache Management for Long Conversational Question Answering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Block Prefill Eviction

[논문리뷰] EpiCache: Episodic KV Cache Management for Long Conversational Question Answering

September 23, 2025

Minsik Cho이 [arXiv]에 게시한 ‘EpiCache: Episodic KV Cache Management for Long Conversational Question Answering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sensitivity-aware Allocation

[논문리뷰] EpiCache: Episodic KV Cache Management for Long Conversational Question Answering

September 23, 2025

Minsik Cho이 [arXiv]에 게시한 ‘EpiCache: Episodic KV Cache Management for Long Conversational Question Answering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning Behaviors

[논문리뷰] FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions

September 23, 2025

tengdai722이 [arXiv]에 게시한 ‘FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questio...

Back to Top ↑

Contamination-Free

[논문리뷰] FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions

September 23, 2025

tengdai722이 [arXiv]에 게시한 ‘FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questio...

Back to Top ↑

Open-Source AI

[논문리뷰] From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem

September 23, 2025

Ahmed E. Hassan이 [arXiv]에 게시한 ‘From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

License Compliance

[논문리뷰] From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem

September 23, 2025

Ahmed E. Hassan이 [arXiv]에 게시한 ‘From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

License Drift

[논문리뷰] From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem

September 23, 2025

Ahmed E. Hassan이 [arXiv]에 게시한 ‘From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AI Supply Chain

[논문리뷰] From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem

September 23, 2025

Ahmed E. Hassan이 [arXiv]에 게시한 ‘From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hugging Face

[논문리뷰] From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem

September 23, 2025

Ahmed E. Hassan이 [arXiv]에 게시한 ‘From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GitHub

[논문리뷰] From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem

September 23, 2025

Ahmed E. Hassan이 [arXiv]에 게시한 ‘From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

LicenseRec

[논문리뷰] From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem

September 23, 2025

Ahmed E. Hassan이 [arXiv]에 게시한 ‘From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Legal Risk

[논문리뷰] From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem

September 23, 2025

Ahmed E. Hassan이 [arXiv]에 게시한 ‘From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Token Heterogeneity

[논문리뷰] From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token’s Nature

September 23, 2025

Bin Cui이 [arXiv]에 게시한 ‘From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token’s Nature’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Advantage Redistribution

[논문리뷰] From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token’s Nature

September 23, 2025

Bin Cui이 [arXiv]에 게시한 ‘From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token’s Nature’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Asymmetric Clipping

[논문리뷰] From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token’s Nature

September 23, 2025

Bin Cui이 [arXiv]에 게시한 ‘From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token’s Nature’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Entropy-based RL

[논문리뷰] From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token’s Nature

September 23, 2025

Bin Cui이 [arXiv]에 게시한 ‘From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token’s Nature’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Geometric Reasoning

[논문리뷰] GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning

September 23, 2025

Hou Pong Chan이 [arXiv]에 게시한 ‘GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Two-stage Training

[논문리뷰] GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning

September 23, 2025

Hou Pong Chan이 [arXiv]에 게시한 ‘GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

GeoPQA Benchmark

[논문리뷰] GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning

September 23, 2025

Hou Pong Chan이 [arXiv]에 게시한 ‘GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Perceptual Bottleneck

[논문리뷰] GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning

September 23, 2025

Hou Pong Chan이 [arXiv]에 게시한 ‘GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

AI Agency

[논문리뷰] LIMI: Less is More for Agency

September 23, 2025

happyZYM이 [arXiv]에 게시한 ‘LIMI: Less is More for Agency’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Less Is More

[논문리뷰] LIMI: Less is More for Agency

September 23, 2025

happyZYM이 [arXiv]에 게시한 ‘LIMI: Less is More for Agency’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agentic Intelligence

[논문리뷰] LIMI: Less is More for Agency

September 23, 2025

happyZYM이 [arXiv]에 게시한 ‘LIMI: Less is More for Agency’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Efficiency Principle

[논문리뷰] LIMI: Less is More for Agency

September 23, 2025

happyZYM이 [arXiv]에 게시한 ‘LIMI: Less is More for Agency’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-modal Foundation Model

[논문리뷰] Mano Report

September 23, 2025

Minghui Wu이 [arXiv]에 게시한 ‘Mano Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Simulated Environment

[논문리뷰] Mano Report

September 23, 2025

Minghui Wu이 [arXiv]에 게시한 ‘Mano Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Error Recovery

[논문리뷰] Mano Report

September 23, 2025

Minghui Wu이 [arXiv]에 게시한 ‘Mano Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Web Automation

[논문리뷰] Mano Report

September 23, 2025

Minghui Wu이 [arXiv]에 게시한 ‘Mano Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Late Interaction

[논문리뷰] MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction

September 23, 2025

Xintao Chen이 [arXiv]에 게시한 ‘MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Meta Tokens

[논문리뷰] MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction

September 23, 2025

Xintao Chen이 [arXiv]에 게시한 ‘MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Matryoshka Representation Learning

[논문리뷰] MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction

September 23, 2025

Xintao Chen이 [arXiv]에 게시한 ‘MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video Insertion

[논문리뷰] OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

September 23, 2025

Pengze Zhang이 [arXiv]에 게시한 ‘OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Quantization-Aware PEFT

[논문리뷰] QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models

September 23, 2025

Jae-Joon Kim이 [arXiv]에 게시한 ‘QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Walsh-Hadamard Transform

[논문리뷰] QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models

September 23, 2025

Jae-Joon Kim이 [arXiv]에 게시한 ‘QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sparse Adaptation

[논문리뷰] QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models

September 23, 2025

Jae-Joon Kim이 [arXiv]에 게시한 ‘QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Low-bit Quantization

[논문리뷰] QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models

September 23, 2025

Jae-Joon Kim이 [arXiv]에 게시한 ‘QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Model

[논문리뷰] Qwen3-Omni Technical Report

September 23, 2025

Lhma-aslp이 [arXiv]에 게시한 ‘Qwen3-Omni Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Thinker-Talker Architecture

[논문리뷰] Qwen3-Omni Technical Report

September 23, 2025

Lhma-aslp이 [arXiv]에 게시한 ‘Qwen3-Omni Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Low-latency

[논문리뷰] Qwen3-Omni Technical Report

September 23, 2025

Lhma-aslp이 [arXiv]에 게시한 ‘Qwen3-Omni Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cross-modal Reasoning

[논문리뷰] Qwen3-Omni Technical Report

September 23, 2025

Lhma-aslp이 [arXiv]에 게시한 ‘Qwen3-Omni Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Real-time Interaction

[논문리뷰] Qwen3-Omni Technical Report

September 23, 2025

Lhma-aslp이 [arXiv]에 게시한 ‘Qwen3-Omni Technical Report’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Symbolic AI

[논문리뷰] Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning

September 23, 2025

Damien Sileo이 [arXiv]에 게시한 ‘Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Adaptive Curricula

[논문리뷰] Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning

September 23, 2025

Damien Sileo이 [arXiv]에 게시한 ‘Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

First-Order Logic

[논문리뷰] Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning

September 23, 2025

Damien Sileo이 [arXiv]에 게시한 ‘Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

PDDL Planning

[논문리뷰] Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning

September 23, 2025

Damien Sileo이 [arXiv]에 게시한 ‘Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Monte Carlo Annotation

[논문리뷰] SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning

September 23, 2025

Zhaopeng Tu이 [arXiv]에 게시한 ‘SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Noise Denoising

[논문리뷰] SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning

September 23, 2025

Zhaopeng Tu이 [arXiv]에 게시한 ‘SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Robust Learning

[논문리뷰] SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning

September 23, 2025

Zhaopeng Tu이 [arXiv]에 게시한 ‘SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Supervision

[논문리뷰] SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning

September 23, 2025

Zhaopeng Tu이 [arXiv]에 게시한 ‘SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Contamination Resistance

[논문리뷰] SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

September 23, 2025

Yannis Yiming He이 [arXiv]에 게시한 ‘SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Enterprise Software

[논문리뷰] SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

September 23, 2025

Yannis Yiming He이 [arXiv]에 게시한 ‘SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Language Model Pretraining

[논문리뷰] Synthetic bootstrapped pretraining

September 23, 2025

Emmanuel Candès이 [arXiv]에 게시한 ‘Synthetic bootstrapped pretraining’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Inter-document Correlation

[논문리뷰] Synthetic bootstrapped pretraining

September 23, 2025

Emmanuel Candès이 [arXiv]에 게시한 ‘Synthetic bootstrapped pretraining’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bootstrapping

[논문리뷰] Synthetic bootstrapped pretraining

September 23, 2025

Emmanuel Candès이 [arXiv]에 게시한 ‘Synthetic bootstrapped pretraining’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Concept Learning

[논문리뷰] Synthetic bootstrapped pretraining

September 23, 2025

Emmanuel Candès이 [arXiv]에 게시한 ‘Synthetic bootstrapped pretraining’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Video LLMs

[논문리뷰] TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

September 23, 2025

Shaohui Jiao이 [arXiv]에 게시한 ‘TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Off-policy Learning

[논문리뷰] TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

September 23, 2025

Shaohui Jiao이 [arXiv]에 게시한 ‘TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reward Shaping

[논문리뷰] TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

September 23, 2025

Shaohui Jiao이 [arXiv]에 게시한 ‘TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Turkish NLP

[논문리뷰] Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

September 23, 2025

Fatma Betül Terzioğlu이 [arXiv]에 게시한 ‘Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Token Classification

[논문리뷰] Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

September 23, 2025

Fatma Betül Terzioğlu이 [arXiv]에 게시한 ‘Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

ModernBERT

[논문리뷰] Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

September 23, 2025

Fatma Betül Terzioğlu이 [arXiv]에 게시한 ‘Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Collaborative Filtering

[논문리뷰] Understanding Embedding Scaling in Collaborative Filtering

September 23, 2025

Yonghui Yang이 [arXiv]에 게시한 ‘Understanding Embedding Scaling in Collaborative Filtering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Embedding Scaling

[논문리뷰] Understanding Embedding Scaling in Collaborative Filtering

September 23, 2025

Yonghui Yang이 [arXiv]에 게시한 ‘Understanding Embedding Scaling in Collaborative Filtering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Noise Robustness

[논문리뷰] Understanding Embedding Scaling in Collaborative Filtering

September 23, 2025

Yonghui Yang이 [arXiv]에 게시한 ‘Understanding Embedding Scaling in Collaborative Filtering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Performance Degradation

[논문리뷰] Understanding Embedding Scaling in Collaborative Filtering

September 23, 2025

Yonghui Yang이 [arXiv]에 게시한 ‘Understanding Embedding Scaling in Collaborative Filtering’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Cultural Heritage

[논문리뷰] VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery

September 23, 2025

Shiya Huang이 [arXiv]에 게시한 ‘VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Ancient Greek Pottery

[논문리뷰] VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery

September 23, 2025

Shiya Huang이 [arXiv]에 게시한 ‘VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Image Diffusion

[논문리뷰] VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models

September 23, 2025

Sunghyun Cho이 [arXiv]에 게시한 ‘VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sparse Anchor Views

[논문리뷰] VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models

September 23, 2025

Sunghyun Cho이 [arXiv]에 게시한 ‘VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Small VLMs

[논문리뷰] When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs

September 23, 2025

Anand Mishra이 [arXiv]에 게시한 ‘When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs’ 논문에...

Back to Top ↑

Large VLMs

[논문리뷰] When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs

September 23, 2025

Anand Mishra이 [arXiv]에 게시한 ‘When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs’ 논문에...

Back to Top ↑

Model Parity Alignment

[논문리뷰] When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs

September 23, 2025

Anand Mishra이 [arXiv]에 게시한 ‘When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs’ 논문에...

Back to Top ↑

Arabic OCR

[논문리뷰] Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR

September 24, 2025

Zeina Aldallal이 [arXiv]에 게시한 ‘Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Markdown Conversion

[논문리뷰] Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR

September 24, 2025

Zeina Aldallal이 [arXiv]에 게시한 ‘Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Conditional Generative Models

[논문리뷰] CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching

September 24, 2025

Rui Qian이 [arXiv]에 게시한 ‘CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reparameterization

[논문리뷰] CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching

September 24, 2025

Rui Qian이 [arXiv]에 게시한 ‘CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Latent Space Alignment

[논문리뷰] CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching

September 24, 2025

Rui Qian이 [arXiv]에 게시한 ‘CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visuomotor Policies

[논문리뷰] Do You Need Proprioceptive States in Visuomotor Policies?

September 24, 2025

Yushen Liang이 [arXiv]에 게시한 ‘Do You Need Proprioceptive States in Visuomotor Policies?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Spatial Generalization

[논문리뷰] Do You Need Proprioceptive States in Visuomotor Policies?

September 24, 2025

Yushen Liang이 [arXiv]에 게시한 ‘Do You Need Proprioceptive States in Visuomotor Policies?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Proprioception

[논문리뷰] Do You Need Proprioceptive States in Visuomotor Policies?

September 24, 2025

Yushen Liang이 [arXiv]에 게시한 ‘Do You Need Proprioceptive States in Visuomotor Policies?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

State-free Policies

[논문리뷰] Do You Need Proprioceptive States in Visuomotor Policies?

September 24, 2025

Yushen Liang이 [arXiv]에 게시한 ‘Do You Need Proprioceptive States in Visuomotor Policies?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

End-Effector Control

[논문리뷰] Do You Need Proprioceptive States in Visuomotor Policies?

September 24, 2025

Yushen Liang이 [arXiv]에 게시한 ‘Do You Need Proprioceptive States in Visuomotor Policies?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Data Efficiency

[논문리뷰] Do You Need Proprioceptive States in Visuomotor Policies?

September 24, 2025

Yushen Liang이 [arXiv]에 게시한 ‘Do You Need Proprioceptive States in Visuomotor Policies?’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Sparse Voxels

[논문리뷰] GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction

September 24, 2025

Jin Zheng이 [arXiv]에 게시한 ‘GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Geometric Accuracy

[논문리뷰] GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction

September 24, 2025

Jin Zheng이 [arXiv]에 게시한 ‘GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Monocular Depth

[논문리뷰] GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction

September 24, 2025

Jin Zheng이 [arXiv]에 게시한 ‘GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Voxel Uncertainty

[논문리뷰] GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction

September 24, 2025

Jin Zheng이 [arXiv]에 게시한 ‘GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

High-Quality Rendering

[논문리뷰] HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis

September 24, 2025

Dan Xu이 [arXiv]에 게시한 ‘HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hybrid Representation

[논문리뷰] HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis

September 24, 2025

Dan Xu이 [arXiv]에 게시한 ‘HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Acceleration Framework

[논문리뷰] Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation

September 24, 2025

Jianbin Zheng이 [arXiv]에 게시한 ‘Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Diffusion Distillation

[논문리뷰] Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation

September 24, 2025

Jianbin Zheng이 [arXiv]에 게시한 ‘Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Bias

[논문리뷰] Large Language Models Discriminate Against Speakers of German Dialects

September 24, 2025

Katharina von der Wense이 [arXiv]에 게시한 ‘Large Language Models Discriminate Against Speakers of German Dialects’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

German Dialects

[논문리뷰] Large Language Models Discriminate Against Speakers of German Dialects

September 24, 2025

Katharina von der Wense이 [arXiv]에 게시한 ‘Large Language Models Discriminate Against Speakers of German Dialects’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Stereotypes

[논문리뷰] Large Language Models Discriminate Against Speakers of German Dialects

September 24, 2025

Katharina von der Wense이 [arXiv]에 게시한 ‘Large Language Models Discriminate Against Speakers of German Dialects’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Implicit Association Test

[논문리뷰] Large Language Models Discriminate Against Speakers of German Dialects

September 24, 2025

Katharina von der Wense이 [arXiv]에 게시한 ‘Large Language Models Discriminate Against Speakers of German Dialects’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Decision Making

[논문리뷰] Large Language Models Discriminate Against Speakers of German Dialects

September 24, 2025

Katharina von der Wense이 [arXiv]에 게시한 ‘Large Language Models Discriminate Against Speakers of German Dialects’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Self-Distillation

[논문리뷰] Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

September 24, 2025

Yifeng Jiang이 [arXiv]에 게시한 ‘Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Dynamic 4D Generation

[논문리뷰] Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

September 24, 2025

Yifeng Jiang이 [arXiv]에 게시한 ‘Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Monocular Input

[논문리뷰] Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

September 24, 2025

Yifeng Jiang이 [arXiv]에 게시한 ‘Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Advantage Function

[논문리뷰] MAPO: Mixed Advantage Policy Optimization

September 24, 2025

Xuankun Rong이 [arXiv]에 게시한 ‘MAPO: Mixed Advantage Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Trajectory Certainty

[논문리뷰] MAPO: Mixed Advantage Policy Optimization

September 24, 2025

Xuankun Rong이 [arXiv]에 게시한 ‘MAPO: Mixed Advantage Policy Optimization’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

MLLM Efficiency

[논문리뷰] MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe

September 24, 2025

Wenshuo Ma이 [arXiv]에 게시한 ‘MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multimodal Transformer

[논문리뷰] MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe

September 24, 2025

Wenshuo Ma이 [arXiv]에 게시한 ‘MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

3D-Resampler

[논문리뷰] MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe

September 24, 2025

Wenshuo Ma이 [arXiv]에 게시한 ‘MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Document AI

[논문리뷰] MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe

September 24, 2025

Wenshuo Ma이 [arXiv]에 게시한 ‘MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Hybrid Reinforcement Learning

[논문리뷰] MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe

September 24, 2025

Wenshuo Ma이 [arXiv]에 게시한 ‘MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Robotics Data Curation

[논문리뷰] OpenGVL - Benchmarking Visual Temporal Progress for Data Curation

September 24, 2025

Viktor Petrenko이 [arXiv]에 게시한 ‘OpenGVL - Benchmarking Visual Temporal Progress for Data Curation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Visual Temporal Progress

[논문리뷰] OpenGVL - Benchmarking Visual Temporal Progress for Data Curation

September 24, 2025

Viktor Petrenko이 [arXiv]에 게시한 ‘OpenGVL - Benchmarking Visual Temporal Progress for Data Curation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Generative Value Learning (GVL)

[논문리뷰] OpenGVL - Benchmarking Visual Temporal Progress for Data Curation

September 24, 2025

Viktor Petrenko이 [arXiv]에 게시한 ‘OpenGVL - Benchmarking Visual Temporal Progress for Data Curation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Task Progress Prediction

[논문리뷰] OpenGVL - Benchmarking Visual Temporal Progress for Data Curation

September 24, 2025

Viktor Petrenko이 [arXiv]에 게시한 ‘OpenGVL - Benchmarking Visual Temporal Progress for Data Curation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Value-Order Correlation (VOC)

[논문리뷰] OpenGVL - Benchmarking Visual Temporal Progress for Data Curation

September 24, 2025

Viktor Petrenko이 [arXiv]에 게시한 ‘OpenGVL - Benchmarking Visual Temporal Progress for Data Curation’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Next-segment Reasoning

[논문리뷰] Reinforcement Learning on Pre-Training Data

September 24, 2025

Evander Yang이 [arXiv]에 게시한 ‘Reinforcement Learning on Pre-Training Data’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Geospatial Reasoning

[논문리뷰] VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction

September 24, 2025

So Fukuda이 [arXiv]에 게시한 ‘VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Temporal Reasoning

[논문리뷰] VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction

September 24, 2025

So Fukuda이 [arXiv]에 게시한 ‘VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Travel Itinerary Reconstruction

[논문리뷰] VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction

September 24, 2025

So Fukuda이 [arXiv]에 게시한 ‘VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Agent System

[논문리뷰] VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction

September 24, 2025

So Fukuda이 [arXiv]에 게시한 ‘VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

VLOG

[논문리뷰] VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction

September 24, 2025

So Fukuda이 [arXiv]에 게시한 ‘VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Voxel-Aligned Prediction

[논문리뷰] VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

September 24, 2025

Haoxiao Wang이 [arXiv]에 게시한 ‘VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Feed-Forward Reconstruction

[논문리뷰] VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

September 24, 2025

Haoxiao Wang이 [arXiv]에 게시한 ‘VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning Effectiveness

[논문리뷰] What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT

September 24, 2025

Anthony Hartshorn이 [arXiv]에 게시한 ‘What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Failed-Step Fraction

[논문리뷰] What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT

September 24, 2025

Anthony Hartshorn이 [arXiv]에 게시한 ‘What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Reasoning Graph

[논문리뷰] What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT

September 24, 2025

Anthony Hartshorn이 [arXiv]에 게시한 ‘What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT’ 논문에 대한 자세한 리뷰입니다.

Back to Top ↑

Multi-spectral Imagery

[논문리뷰] Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications

September 24, 2025

Genady Beryozkin이 [arXiv]에 게시한 ‘Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications’ 논문에 ...

Back to Top ↑

Gemini 2.5

[논문리뷰] Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications

September 24, 2025

Genady Beryozkin이 [arXiv]에 게시한 ‘Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications’ 논문에 ...

Back to Top ↑

Land Cover Classification

[논문리뷰] Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications

September 24, 2025

Genady Beryozkin이 [arXiv]에 게시한 ‘Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications’ 논문에 ...

Back to Top ↑

Pseudo-Image

[논문리뷰] Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications

September 24, 2025

Genady Beryozkin이 [arXiv]에 게시한 ‘Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications’ 논문에 ...

Back to Top ↑